From pb at lpl.univ-aix.fr Fri Feb 2 16:51:13 2001 From: pb at lpl.univ-aix.fr (Philippe Blache) Date: Fri, 2 Feb 2001 17:51:13 +0100 Subject: Appel: TSD-2001 Message-ID: From: tsd2001 Matousek _____________________________________________________________________ This message is posted to several lists. We apologize if you receive multiple copies. Please forward it to everyone who might be interested. _____________________________________________________________________ TTTTTTTT SSSS DDDDD 2222 0000 0000 111 TT SSS SSS DD DDD 222 222 000 000 000 000 1111 TT SSS DD DDD 222 000 000 000 000 11111 TT SSSS DD DD 222 000 000 000 000 111 TT SSS DD DDD 222 000 000 000 000 111 TT SSS SSS DD DDD 2222 000 000 000 000 111 TT SSSS DDDDD 22222222 0000 0000 111 _____________________________________________________________________ An International Conference on Text, Speech and Dialogue (TSD 2001) September 10 - 13, 2001 Zelezna Ruda, Czech Republic _____________________________________________________________________ F I R S T A N N O U N C E M E N T A N D C A L L F O R P A P E R S _____________________________________________________________________ TSD 2001 will be organized by the Faculty of Applied Sciences, University of West Bohemia, Plzen (Pilsen), and the Faculty of Informatics, Masaryk University, Brno, under the auspices of the Dean of the Faculty of Applied Sciences of the University of West Bohemia. Conference topics: ------------------ TSD 2001 will be concerned with topics in the field of natural language processing, in particular: - corpora, texts and transcription; - speech analysis, recognition and synthesis; - their intertwinnig within NL dialogue systems. Topics of the TSD 2001 Conference will include (but are not limited to): - text corpora and tagging; - transcription problems in spoken corpora; - sense disambiguation; - links between text and speech oriented systems; - parsing issues, especially parsing problems in spoken texts; - multilingual issues, especially multilingual dialogue systems; - information retrieval and text/topic summarization; - speech modeling; - speech segmentation; - speech recognition; - text-to-speech synthesis; - speech and motions; - dialogue systems; - development of dialogue strategies; - assistive technologies based on speech and dialogue; - applied systems and software. The official language of the event will be English, but papers on issues relating to text and speech processing in languages other than English are strongly encouraged. Format of the conference: ----------------------- TSD 2001 will be an international conference with a limited number of active participants. The conference program will include presentation of three invited papers by keynote speakers, a limited number of general oral presentations, and a poster/demonstration sessions. Papers will be presented in plenary or topic oriented sessions. A special attention will be paid to the arrangement of thematic oriented poster sections extended by short oral presentations. Proceedings: ------------ The contributions to the conference will be published in proceedings that will be made available to participants at the time of the conference. The proceedings will be published by Springer in the series of Lecture Notes of Artificial Intelligence (LNAI). Venue: ------ The international conference will take place in the comfortable hotel Horizont in Sumava Mountains. The hotel is located 1100 m above sea level in the Bohemian Forest Nature Preserve and 3 km far from the centre of Zelezna Ruda town. Social events: -------------- The international conference will also include some social events and trips to the most popular places - Sumava National Park, Black and Devil's lake, Laka lake, district city of Klatovy, Klenova castle and Grosser Arber in Bayerischer Wald on the German side of the border. How to reach Zelezna Ruda: ----------------------------- Zelezna Ruda has very good train connections with Prague, Pilsen and Munich. Distances of the nearest airports (Prague-Ruzyne, Munich) from Zelezna Ruda are about 200 km. More detailed travel information will be posted on the TSD 2001 Web site in due course. Registration Cost: ------------------ Registration fee is $220 (including meals, accommodation, organizing costs, conference proceedings, social events). Student reductions will be available. Accommodation: -------------- The hotel Horizont has 90 double rooms. Each room has its own shower toilet, telephone, nd TV set. The hotel also offers many attractive hotel services. Important dates: ---------------- March 15, 2001 Preliminary registration and deadline for submission of papers April 30, 2001 Notification of acceptance or rejection May 30, 2001 Camera-ready paper submission Sept. 10-13, 2001 TSD 2001 International program committee: -------------------------------- Frederick Jelinek, USA - general chair Hynek Hermansky, USA - executive chair Genevieve Baudoin, France - speech Frantisek Cermak, Czech Rep. - text Attila Ferencz, Romania - speech Eva Hajicova, Czech Rep. - text, speech Patrick Hanks, GB - text Eduard Hovy, USA - text, speech Adam Kilgariff, GB - text Ivan Kopecek, Czech Rep. - speech, text Steven Krauwer, Netherland - text Karel Kucera, Czech Rep. - text Vaclav Matousek, Czech Rep. - speech Rosamund Moon, GB - text Elmar Noeth, Germany - speech Karel Pala, Czech Rep. - text Nikola Pavesic, Slovenia - speech Vladimir Petkevic, Czech Rep. - text Josef Psutka, Czech Rep. - speech E.G. Schukat-Tallamazini, Germany - speech Pavel Skrelin, Russia - speech Taras Vintsiuk, Ukraine - speech Yorick Wilks, GB - text Organizing committee: --------------------- Vaclav Matousek (chair) Helena Benesova Kamil Ekstein Jana Hesova Svatava Kindlova Jana Kleckova Ivan Kopecek Jana Krutisova Josef Masek Pavel Mautner Roman Moucek Jana Ocelikova Karel Pala Pavel Slavik Petr Sojka Karel Tauser Registration: ------------- The registration fee should be paid directly by bank transfer to: Komercni banka Plzen-mesto, Goethova 1, CZ-305 95 Plzen account number : 4811530257/0100 purchase order : 5204/0003/00 special ID code: your birth date in the form YYMMDD (year - month - day), e.g. 550425 account holder: University of West Bohemia, Univerzitni 8, CZ - 306 14 Plzen stating: TSD 2001 and your name Submission of papers: ------------------------ Full papers (max. 8 pages in Springer LNCS format) will be required to reach a decision about acceptance or rejection. First versions of papers submitted for acceptance could be prepared in ASCII format only. Full papers should be submitted to the TSD 2001 Secretariat, preferably by email (tsd2001 at kiv.zcu.cz), by March 15th, 2001. Please contact the Conference Secretariat if receipt of your email submission is not acknowledged within 7 days. It is intended to post abstracts of papers accepted on the TSD 2001 web site in advance of the conference. Please include the following information with your paper: - title of paper, author name(s), author(s) affiliation(s) - e-mail/address/fax of author(s) contact(s) - presentation preference: oral or poster/demonstration. Authors of accepted papers will be requested to send their papers in LateX and PostScript form (in LNCS format) to the conference secretariat by e-mail before June 1st. LaTeX word processor is required. Format instructions (and LNCS LaTeX format) will be available to authors on the TSD 2001 Web site. The conference proceedings will be traditionally published by Springer-Verlag in LNCS/LNAI series (numbers of previous proceedings - LNAI 1692 and LNAI 1902). Conference secretariat: ----------------------- All correspondence regarding the conference should be addressed to: Ms. Helena Benesova University of West Bohemia in Pilsen Faculty of Applied Sciences Department of Computer Science Univerzitni 8 CZ - 306 14 PLZEN Czech Republic Tel: (+420 19) 7491 212, 27 62 50 Fax: (+420 19) 7491 213 E-mail: tsd2001 at kiv.zcu.cz To obtain more information please visit the TSD 2001 Web site: http://www-kiv.zcu.cz/events/tsd2001 ---------------------------- cut here ------------------------------- TSD 2001, September 10-13, 2001, Zelezna Ruda, Czech Republic Preliminary registration Please return this form to the Conference Secretariat Name: Affiliation: Address: Phone: Fax: E-mail: I would like to participate in TSD 2001 as a [ ] Full participiant [ ] Student [ ] I propose to submit a full paper entitled: Preferred presentation: [ ] oral [ ] demo / poster ___________________________________________________________________ Message diffus� par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From pb at lpl.univ-aix.fr Fri Feb 2 16:51:58 2001 From: pb at lpl.univ-aix.fr (Philippe Blache) Date: Fri, 2 Feb 2001 17:51:58 +0100 Subject: Appel: CIAA-2001 Message-ID: From: Maurel Denis My apologies if you have already seen this, or if you receive more than one copy! ---------- SECOND CALL FOR PAPERS Sixth International Conference on Implementation and Application of Automata CIAA 2001 University of Pretoria July 23-25, 2001 ---------- This conference concerns research on all aspects of implementation and application of automata and related structures. Automata theory is the foundation of computer science. Its applications have spread to almost all areas of computer science and many other disciplines. In addition, there is a growing number of software systems designed to manipulate automata, regular expressions, grammars, and related structures; examples include AGL, AMORE, Automate, FADELA, FinITE, FireLite, FLAP, FSM, Grail, INR, MONA, and Turing's World. The purpose of this conference is to bring together members of the academic, research, and industrial community who have an interest in implementation and application of automata to demonstrate and analyze their work and to explain the problems they have been solving. SCOPE OF THE CONFERENCE We solicit papers and demos on all aspects of implementation and application of automata and related structures, including but not limited to: * Bioinformatics and automata * Complexity of automata operations * Compilers and automata * Computer-aided verification and automata * Concurrency and automata * Data structure design for automata * Data and image compression and automata * Design and architecture of automata software * Digital libraries and automata * Document engineering and automata * Editors, environments and automata * Experimental studies and practical experiences * Industrial applications and automata * Natural language processing and automata * Networking and automata * New algorithms for manipulating automata * Object-Oriented Modeling and automata * Pattern-matching and automata * Speech and speaker recognition and automata * Structured and semi-structured documents and automata * Symbolic manipulation environments for automata * Teaching and automata * Text processing and automata * Techniques for graphical display of automata * VLSI and automata * Viruses, related phenomena and automata * World-wide web and automata SUBMISSION OF PAPERS Authors are requested to submit an electronic version (in PostScript or LaTeX form) or six hard copies of an extended abstract (arriving) by April 2, 2001. An extended abstract should start with the title, each author's name, affiliation, and e-mail address, and a one-paragraph summary of the results and ideas, and be sent to: ciaa2001 at cs.up.ac.za or CIAA 2001 ATTENTION: OPV5-20 Department of Computer Science University of Pretoria Pretoria, South Africa 0002 The extended abstract should provide sufficient detail to allow the Program Committee to evaluate its validity, quality, and relevance to the conference. The extended abstract should be at most ten (10) pages long using 11-point font with ample margins. If appropriate, proof details omitted in the paper may be added in an appendix. Authors will be notified of acceptance or rejection by May 1, 2001. Final copies of accepted papers must be submitted by June 18, 2001. We expect the proceedings to appear in the Springer-Verlag Lecture Notes in Computer Science Series after the conference. (See for example, LNCS 1260 and LNCS 1436 for the proceedings of two previous conferences.) We will distribute a preproceedings for participants at the conference. Extended versions of selected papers from the proceedings of the conference series will be solicited for publication in special issues of Theoretical Computer Science (TCS) and International Journal of Foundations of Computer Science (IJFCS), alternating each year with the CIAA 2001 special issue appearing in TCS. DEMOS We encourage the submission of software demos. Developers wishing to demonstrate their software should submit a two-page description to the address given above by April 2, 2001, outlining the design of their system and their computing needs (if any). INVITED SPEAKERS Gregor v. Bochmann, Ottawa, Canada, CIAA 2001 PROGRAM COMMITTEE B. Boigelot (Liege) J.-M. Champarnaud (Rouen) M. Crochemore (Marne la Vallee) O. Ibarra (UCSB) L. Karttunen (Xerox Europe) N. Klarlund (AT&T) D. Maurel (Tours) M. Mohri (AT&T) J.-E. Pin (Paris) K. Salomaa (Queen's) H. Seidl (Trier) B. Watson (Co-chair) (Pretoria) D. Wood (Co-Chair) (HKUST) S. Yu (Western Ontario) IMPORTANT DATES April 2, 2001 Submission deadline May 1, 2001 Acceptances and rejections sent out June 18, 2001 Submission deadline for preproceedings July 23-25, 2001 Conference dates Sept. 21, 2001 Submission deadline for SV-LNCS SPONSORING ORGANIZATIONS ACM SIGACT, EATCS, University of Pretoria PREVIOUS CONFERENCES CIAA 2000 website WIA'99 website WIA'98 website CIAA 2001 WEB SITES Pretoria Site Hong Kong Site ---------- Prof.Dr. Bruce W. Watson Co-chair of the 2001 Conference on Implementation and Application of Automata bwatson at OpenFIRE.org or bwatson at cs.up.ac.za or watson at win.tue.nl Please DO NOT send me any large emails without asking first. ___________________________________________________________________ Message diffus� par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From pb at lpl.univ-aix.fr Fri Feb 2 16:53:27 2001 From: pb at lpl.univ-aix.fr (Philippe Blache) Date: Fri, 2 Feb 2001 17:53:27 +0100 Subject: Appel: TAL Special Issue Message-ID: From: Pierrette Bouillon %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% ***************************************************************** Call for papers ***************************************************************** SEMANTIC LEXICONS IN NATURAL LANGUAGE PROCESSING Special issue of the French journal TAL edited by: Pierrette Bouillon (TIM/ISSCO, Genève) and Evelyne Viegas (Microsoft/Natural Language Group, Redmond) Submission deadline: April 1, 2001 http://www.atala.org/tal/appel-semlex.html **************************************************************** SCOPE No one would argue about the importance of semantic lexicons for Natural Language Processing applications such as machine translation, automatic indexing, information extraction, text generation, etc. However, there is no agreement on the type of information to use, how to represent it or how to acquire it automatically. This special issue directly addresses this difficult topic by investigating how lexical semantic theories relate to applications in NLP. We will emphasize the following questions: - Which theory for which application? - How to acquire information automatically? - How to use it in applications? TOPICS (NOT LIMITATIVE) - Acquisition of semantic lexicons - Lexical semantics in NLP applications - Generic versus specific resources? - Which lexical semantic theory for which application? - Types of lexical information - Reuse of existing lexical data FORMAT AND SUBMISSIONS Authors must use the HERMES style files for LateX and Word at . Submissions (30 pages maximum, double spaced, Helvetica 12) must be sent electronically to Pierrette Bouillon () and Evelyne Viegas (). LANGUAGE Articles can be written in French or in English, but English will only be accepted from non-French speaking authors. PROGRAM COMMITTEE - Pierrette Bouillon (TIM/ISSCO, Genève) - Paul Buitelaar (DFKI, Saarbrücken) - Nicoletta Calzolari (Istituto Di Linguistica Computazionale, Pisa) - Ann Copestake (Cambridge University, Cambridge) - Cécile Fabre (Univ. Toulouse-Le-Mirail, Toulouse) - Christiane Fellbaum (Princeton University, Princeton) - Thierry Fontenelle (Luxembourg) - Mari Olsen (Microsoft, Natural Language Group, Redmond) - Pierre Popowich (Gavagai Technology, Vancouver) - James Pustejovsky (Brandeis University) - Pascale Sebillot (Irisa, Rennes) - Frédérique Segond (Xerox Research Centre Europe, Grenoble) - Evelyne Viegas (Microsoft, Natural Language Group, Redmond) - Piek Vossen (SailLabs, Antwerpen) - Rémi Zajac (New Mexico State University, Computing Research Laboratory) JOURNAL T.A.L. (http://www.atala.org/tal/) The international journal Traitement Automatique des Langues (TAL) has been published since 1969 by the French Association pour le Traitement Automatique des Langues (ATALA) with the support of the Centre National pour la Recherche Scientifique (CNRS). The journal TAL covers all fields of computational linguistics and its aim is to provide mainly (but not only) French speaking researchers and students with publications in all domains of computational linguistics. It appears three times a year and is distributed by HERMES. T.A.L. EDITORIAL BOARD Ann Abeillé (Université Paris 7) Pierrette Bouillon (TIM/ISSCO, Genève) Philippe Blache (CNRS, Aix-en-Provence) -- Chief Editor Danièle Clément (Bergische Universität Wuppertal) Christophe d'Alessandro (LIMSI-CNRS, Orsay) -- Chief Editor Anne Condamines (CNRS, Toulouse le Mirail) Claire Gardent (Universität des Saarlandes) -- Chief Editor Marc El-Bèze (Université d'Avignon) Jean-Louis Lebrave (CNRS, Paris) Piet Mertens (Katholieke Universiteit Leuven) Évelyne Tzoukermann (Bell Labs) Bernard Victorri (ENS, Paris) Pierre Zweigenbaum (AP-HP, Paris 6) %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% --Boundary_(ID_AgsLXsl9GXQ6uyPwRMwh+w)-- ___________________________________________________________________ Message diffusé par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From pb at lpl.univ-aix.fr Fri Feb 2 16:53:41 2001 From: pb at lpl.univ-aix.fr (Philippe Blache) Date: Fri, 2 Feb 2001 17:53:41 +0100 Subject: Appel: TALN'2001 (Workshops) Message-ID: From: Maurel Denis ********************************************************************** * * TALN 2001 * Traitement Automatique du Langage Naturel * * Universite de Tours * du lundi 2 au jeudi 5 juillet 2001 * * http://www.li.univ-tours.fr/taln-recital-2001/ * mailto::taln2001 at univ-tours.fr * ********************************************************************** TUTORIELS (TUTORIALS): Le traitement automatique des collocations (Béatrice Daille et Geoffrey Williams) Formal Languages for Linguists: Classical and Nonclassical Models (Carlos Martin Vide) Grammaires de dépendance formelles et théorie Sens-Texte (Sylvain Kahane) Intex et ses applications informatiques (Max Silberztein) CONFERENCES ASSOCIEES (WORKSHOPS) Ingenierie de la Langue et handicap (Jean-Yves Antoine et Brigitte Le Pevedic) Traduction automatique et applications en grandeur réelle (Jean Senellart) ___________________________________________________________________ Message diffusé par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From pb at lpl.univ-aix.fr Fri Feb 2 16:53:49 2001 From: pb at lpl.univ-aix.fr (Philippe Blache) Date: Fri, 2 Feb 2001 17:53:49 +0100 Subject: Publication: Journal TAL Message-ID: From: Christian Jacquemin +-----------------------------------------------+ I Revue T.A.L. I I (Le traitement automatique des langues) I I I I http://www.atala.org/tal/tal.html I +-----------------------------------------------+ "Traitement automatique des langues pour la recherche d'information" Vol. 41, Num. 2, Janvier 2001 -------------- Sommaire Christian JACQUEMIN : Présentation du numéro sur le traitement automatique des langues pour la recherche d'information Patrice BELLOT, Marc EL-BÈZE : Classification locale non supervisée pour la recherche documentaire Pierrette BOUILLON, Cécile FABRE, Pascale SÉBILLOT, Laurence JACQMIN : Apprentissage de ressources lexicales pour l'extension de requêtes Béatrice DAILLE, Jean ROYAUTÉ, Xavier POLANCO : Évaluation d'une plate-forme d'indexation de termes complexes Georgette DAL, Fiammetta NAMER : Génération et analyse automatiques de ressources lexicales construites utilisables en recherche d'informations Gael Harry DIAS, Sylvie GUILLORÉ, Jean-Claude BASSANO, José Gabriel PEREIRA LOPES : Extraction automatique d'unités lexicales complexes : Un enjeu fondamental pour la recherche documentaire Éric GAUSSIER, Gregory GREFENSTETTE, David HULL, Claude ROUX : Recherche d'information en français et traitement automatique des langues Diego MOLLA, Rolf SCHWITTER, Michael HESS and Rachel FOURNIER : EXTRANS, An Answer Extraction System Fiammetta NAMER : FLEMM : Un analyseur flexionnel du français à base de règles Martin RAJMAN, Romaric BESANCON, Jean-Cédric CHAPPELIER : Le modèle DSIR: Une approche à base de sémantique distributionnelle pour la recherche documentaire -------------- Tous les adhérents de l'ATALA reçoivent gratuitement la revue T.A.L. Pour devenir adhérent : http://www.atala.org/adhesion.html Vous pouvez acheter le numéro auprès de Hermès Sciences : hermes at iway.fr http://www.editions-hermes.fr/ ___________________________________________________________________ Message diffusé par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From pb at lpl.univ-aix.fr Fri Feb 2 16:54:44 2001 From: pb at lpl.univ-aix.fr (Philippe Blache) Date: Fri, 2 Feb 2001 17:54:44 +0100 Subject: Appel: Phonology (GdR 1954) Message-ID: From: Jean-Pierre Angoujard A DIFFUSER TRES LARGEMENT / PLEASE POST APPEL A COMMUNICATION / CALL FOR PAPERS 3ème JOURNÉES INTERNATIONALES DU GDR " PHONOLOGIE " 3rd INTERNATIONAL PHONOLOGY MEETING OF THE GDR 1954 NANTES / FRANCE 30 mai ­ 1er juin 2001 / 2001 May 30th ­ June 1st Le Groupe de recherche en phonologie (GDR 1954) du C.N.R.S. organise ses 3ème Journées Internationales à Nantes. Vous êtes invités à proposer des contributions dans tout domaine en rapport avec la phonologie (30 min. de présentation et 10 min. de discussion). The research group (GDR) in phonology of the French National Center for Scientific Research (C.N.R.S.) invites submissions for its 3rd International Phonology Meeting (30 min. presentation plus 10 min. discussion). Scope : any topic related to phonology. Les auteurs sont invités à soumettre un résumé anonyme (2 pages A4 maximum). Les noms et adresses des auteurs devront apparaître sur une feuille séparée. Authors are invited to submit an anonymous abstract not exceeding 2 A4 or US quarto pages. Authors¹ names and addresses should be sent on a separate page. LANGUES / WORKING LANGUAGES : français et anglais / English and French DATES A RETENIR / IMPORTANT DATES : Date limite de soumission / Deadline for submission : 25 mars 2001 / 2001 March 25th Notification des acceptations / Notification to authors : 27 avril 2001 / 2001 April 27th COMITE NATIONAL / NATIONAL COMMITTEE J.-P. ANGOUJARD (Université de Nantes) G. BERGOUNIOUX (Université d¹Orléans) N. CLEMENTS (CNRS, Paris) J. DURAND (Université de Toulouse 2) B. LAKS (Université Paris 10) COMITE SCIENTIFIQUE / SCIENTIFIC COMMITTEE F. DELL (CNRS, Paris) D. HIRST ( CNRS, Aix-en-Provence) M. KLEIN (Université Paris 10) M. KENSTOWICZ (MIT) J. LOWENSTAMM (Université Paris 7) Ch. LYCHE (Oslo / TromsO) M. PLENAT (CNRS, Toulouse) P. SAUZET (Université Paris 8) N. VALLEE (ICP, Grenoble) S. WAUQUIER-GRAVELINES (Université de Nantes) ORGANISATION / ORGANISERS Jean-Pierre ANGOUJARD ; Sandrine FERRÉ ; Delphine POURIN. Equipe " Acoustique, Acquisition et Interprétation " (AAI, JE 2220), Université de Nantes : Les propositions de communications doivent être envoyées à Jean-Pierre ANGOUJARD, soit par courrier postal soit par courrier électronique (recommandé). Please send submissions to Jean-Pierre ANGOUJARD (electronic submissions is recommended) : Jean-Pierre Angoujard " Acoustique, Acquisition et Interprétation " Faculté des Lettres et Sciences Humaines Chemin de la Censive-du-Tertre BP 81227 44312 NANTES Cedex 3 France mél / e-mail : jean-pierre.angoujard at humana.univ-nantes.fr ___________________________________________________________________ Message diffusé par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From pb at lpl.univ-aix.fr Mon Feb 5 11:11:22 2001 From: pb at lpl.univ-aix.fr (Philippe Blache) Date: Mon, 5 Feb 2001 12:11:22 +0100 Subject: LN: Passage de temoin (New editor) Message-ID: From: "Philippe Blache" Chers collegues, Ceci est mon dernier envoi sur la liste LN en tant que moderateur : c'est desormais Alexis Nasr (alexis.nasr at lim.univ-mrs.fr) qui assurera l'edition de cette liste, en collaboration avec Thierry Hamon (Thierry.Hamon at lipn.univ-paris13.fr). Je remercie grandement Alexis d'avoir accepte de prendre en charge cette tache. LN est un outil d'information extremement important pour notre communaute. Je suis tres heureux d'y avoir contribue et je suis certain qu'un nouveau dynamisme saura lui etre insufle par Alexis et Thierry. Cordialement, Philippe ---------------- For those of you who don't understand French: the new LN editor is Alexis Nasr (alexis.nasr at lim.univ-mrs.fr). Thank you for your interest in LN ! --------------------------------------------------------------------------- Philippe Blache | tel: +33 (0)442.95.36.36 LPL - Universite de Provence | fax: +33 (0)442.59.50.96 29, Avenue Robert Schuman | 13621 Aix-en-Provence | email: pb at lpl.univ-aix.fr France | http://www.lpl.univ-aix.fr/~blache --------------------------------------------------------------------------- ___________________________________________________________________ Message diffus� par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Mon Feb 12 17:22:49 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Mon, 12 Feb 2001 18:22:49 +0100 Subject: Jobs: Pre- and Postdoctoral Fellowships DFKI Message-ID: From: Hans Uszkoreit Industry Host R&D Fellowships in the Prestigious Marie Curie Programme Pre- and Postdoctoral Fellowships for applicants from EU Member States and Associated Countries in: Multilingual Information Retrieval Agent Technologies Information Management Content Analysis Text Generation A cooperation between DFKI, Saarbruecken and Innoserve Media Solutions GmbH Details: http://www.dfki.de/~hansu/nice-job-offer.pdf ________________________________________ Prof. Dr. Hans Uszkoreit Scientific Director at DFKI http://www.coli.uni-sb.de/~hansu/ Email: Uszkoreit at dfki.de ___________________________________________________________________ Message diffus� par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Mon Feb 12 17:23:14 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Mon, 12 Feb 2001 18:23:14 +0100 Subject: ATALA: journee du 28 avril Message-ID: From: Benoit Habert ------------------------------------------- JOURNEES de l'ATALA - APPEL A COMMUNICATION ------------------------------------------- Samedi 28 avril 2001 De la langue aux genres et aux types La place des types et des genres textuels dans la description et le traitement automatique d'une langue peut être reconsidérée aujourd'hui à la lumière des corpus et des annotateurs automatiques disponibles mais aussi de l'expérience gagnée à traiter non plus des domaines restreints mais du texte "tout venant", en très grande quantité. Cependant la notion de texte tout-venant doit sans doute être réélaborée ou dépassée. La notion de genre textuel est peu étudiée en linguistique. Elle suscite des débats sur sa définition et son opérativité (Adam 00). Néanmoins, de nombreux travaux (Bronckart 96, Roulet 96) portent sur les genres et leur place dans l'économie des échanges langagiers. L'hypothèse sous-jacente est que les genres organiseraient et réguleraient l'infinie diversité des énoncés (Bakhtine). Maîtriser une langue, ce serait d'abord maîtriser des genres. Ces travaux se trouvent aujourd'hui en mesure, grâce à la multiplication des corpus et des outils d'annotation, de tester effectivement ces hypothèses. On peut ainsi chercher à qualifier les différences significatives entre les genres prédéfinis d'un corpus donné et tester la pertinence du classement initial des documents de ce corpus en fonction de ces genres. On peut également, dans une approche d'apprentissage non supervisé, développer une typologie inductive des textes en les caractérisant par un ensemble de dimensions organisant des traits linguistiques (Biber 88, 95). Le traitement automatique des langues fait de plus en plus appel à de volumineux corpus textuels pour l'acquisition des connaissances qui lui sont nécessaires : cadres de sous-catégorisation des verbes, collocations, enchaînement de catégories, acquisition de catégories sémantiques... L'obstacle actuel n'est donc plus la disponibilité de corpus, mais l'hétérogénéité des données qui sont rassemblées sous ce nom. En effet la qualité des connaissances acquises dépend directement de la maîtrise des caractéristiques du corpus utilisé, qu'il s'agisse de l'étiquetage morphosyntaxique (Biber 93), du parsage (Sekhine 97) ou de la recherche d'information (Karlgren 98). Il importerait alors de (re)connaître les types de textes ou les genres présents dans les corpus utilisés. Les propositions de communication pourront en particulier apporter une contribution sur les questions et les thèmes suivants : . Le profilage de documents : comment répartir un ensemble donné de documents en sous-ensembles homogènes pour les traitements automatiques envisagés ? . L'influence des genres ou des types de textes sur les performances des traitements automatiques : y a-t-il des tâches plus sensibles que d'autres à l'hétérogénéité des données utilisées ? . Retrouve-t-on d'un domaine à un autre des genres ou des types similaires ? . Quelle est la fiabilité d'une répartition d'un ensemble de documents en genres et en types par un ensemble d'individus ? . La description syntaxique et sémantique d'une langue, y compris pour le TAL, doit-elle prendre en compte la variation en genres ? . Les "genres" reconnus dans une communauté langagière donnée sont-ils identifiables de manière automatique ? . Les "genres" reconnus dans une communauté langagière donnée constituent-ils les bonnes "variables" pour expliquer l'hétérogénéité d'un corpus ? Soumission (modalités) Un résumé de deux à quatre pages doit être envoyé avant le 28 février 2001 par courrier électronique uniquement à : François Rastier (lpe2 at ext.jussieu.fr) et à Benoît Habert (habert at limsi.fr) Les notifications d'acceptation seront données pour le 31 mars 2001 Pour plus d'informations sur l'ATALA et sur l'organisation des journées d'études, consultez le site de l'ATALA à l'adresse: http://www.atala.org -- La France est le "pays-de-l'amour-et-des-fleurs", disent gentiment les Japonais. Quel étrange sentiment, non dénué de rêverie, que de se découvrir "has been". François Julien et Thierry Marchaisse, Penser d'un dehors (la Chine). Entretiens d'extrême-Occident, Seuil, 2000, p. 490-491. Benoît Habert Equipe Langues Interprétation Représentations (LIR) - LIMSI, BP 133, F-91403, Orsay Cédex & université Paris X mailto:habert at limsi.fr http://www.limsi.fr/Individu/habert/ Tel : mardi et jeudi (33 1) 69 85 80 22 (fax 80 88) - lundi et vendredi (33 1) 40 97 47 34 (fax 40 73) - Fax (33 1) 45 34 35 76 ___________________________________________________________________ Message diffusé par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Mon Feb 12 17:23:38 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Mon, 12 Feb 2001 18:23:38 +0100 Subject: Conf: TALN 2001 workshop on Machine Translation Message-ID: CALL FOR PARTICIPATION Workshop on Machine Translation "Machine Translation and Large-Scale Applications" 5 July 2001 in conjunction with TALN'2001(2-5 July 2001) TOURS Europe - FRANCE Submission deadline : 15 april 2001 MOTIVATION Against the backdrop of an increasingly multilingual society, the Machine Translation Workshop of TALN'2001 looks at the main challenges to Machine Translation and multilingual NLP. Indeed, MT has seen a remarkable development for the past few years in terms of the number of translation requests (about a million translation requests everyday on the Web) as well as in terms of the different types of formats translated : translation of dynamic resources(FAQ, Web pages, daily papers), emails, requests for search engines, etc. These different types of translations demand different levels of quality, and induce an important associated feedback in the form of additional bilingual dictionaries. At the same time there is a growing need for more specialized translation. For this "specialization" the construction of wide-covering mutlilingual resources is an essential component of this more demanding translation. Because of the increase of the number of contributors (experts or users), the questions of exchange, reusability and incrementability of the translation resources had to be raised. The associated investment (public or private) lead to a general tendency to initiate centralizations (cf. Elra), standards (ISO 12220), transfer formalisms (OLIF), and more generally, to create mutlilingual data exchange formats (UNL). In any case, the choice of a linguistic data support cannot be separated from pragmatic considerations concerning the scale, the volume of additional resources becoming more important than the generic resources. These resources can vary from "simple" terminological resources (aligned lexicons) to more complex resources such as terminological grammars, transfer dictionaries, and graphs/grammars of translation. FOCUS OF THE WORKSHOP The focus of the workshop is not only recent machine translation research and products, but also the latest developments in multilingual language technology. The workshop aims at considering the questions of the construction, the validation and the utilization of large-scale resources applied to machine translation. The papers submitted can be related to the different topics below, but also to some other closely related topics : - use of standardization formalisms on important volumes of data - evaluation and realization of construction tools of such resources (from corpus, monolingual resources...) - integration and conversion of existing resources - validation and "expert" improvement processes - massive parallel acquisition of terminology in the framework of a network of users - management of mutlilingual resources compared to bilingual resources - multilingual extraction and machine translation QUESTIONS AND ISSUES You can either submit an abstract of 5 pages, or a complete version of your paper(up to 10 pages). Submitted papers should be in French or in English (for non French speakers). The abstracts and the papers submitted should conform to the submission format of TALN'2001 (style sheets are available on the TALN'2001 site http://www.li.univ-tours.fr/taln-recital-2001) : Times 12, single-spaced, 10 pages at the most, including figures, examples and references. Authors should send their submission as a file attached to an e-mail (ps, pdf, rtf files, A4 format) at the following e-mail address : workshop-taln at systran.org The e-mail should contain the following information: submission title, authors' names and affiliation. Submissions will be reviewed by two experts of the Program Comittee. The final version of the accepted papers will be published in the workshop proceedings. The papers will give rise to 20 minute presentations followed by 10 minutes of questions. PROGRAM COMITTEE Christian Boitet, CLIPS-IMAG,equipe GETA, Grenoble http://clips.imag.fr/geta Maurice Gross, LADL & UMLV, Marne-la-Vallee Igor Boguslavskij, IPPI PAN, Moscou Georges Carayannis, ELRA & ILSP, Athen Joseph Dichy, Faculte des Langues, Universite Lyon II Pierre-Yves Foucou, SYSTRAN, Paris http://www.systransoft.com Daniel Grasmick, SAP, Waldorf Jean Senellart, SYSTRAN, Paris http://www.systransoft.com Tamas Varadi, Linguistics Institute, Hungarian Academy of Sciences Remi Zajac, CRL/NMSU, Las Cruces, http://crl.nmsu/edu/~rzajac IMPORTANT DATES Submission deadline: 15/04/2001 Notification to authors: 25/04/2001 Final version due (camera-ready) : 15/05/2001 Workshop : 05 July 2001 =========================================================================== ============ APPEL A COMMUNICATION Atelier sur la Traduction Automatique "Traduction automatique et applications en grandeur reelle" le 5 juillet 2001 organise dans le cadre de TALN'2001 (2-5 juillet 2001) TOURS - FRANCE Date limite de soumission : 15 avril 2001 MOTIVATION Dans le contexte d'une societe de plus en plus multilingue, l'Atelier sur la Traduction Automatique de TALN'2001 s'interesse aux principaux defis de la Traduction Automatique et du TAL multilingue. En effet, la Traduction Automatique a connu ces dernieres annees un essor considerable, tant en volume d'utilisation (de l'ordre du million de requetes de traduction quotidiennes sur Internet), qu'en etendue : traduction de ressources dynamiques (FAQ, pages web, quotidiens), de mails, de requetes pour moteurs de recherche... Ces traductions, pour lesquelles les exigences de qualite sont variables, induisent un volume de feedback associe tres important en valeur absolue se presentant sous la forme de dictionnaires additionnels bilingues. Parallelement s'etablit une demande croissante pour des traductions specialisees. Pour cette "specialisation", la constitution de ressources multilingues a large couverture est une composante essentielle d'une traduction pour laquelle l'exigence est beaucoup plus importante. De l'augmentation du nombre d'intervenants (experts ou utilisateurs) decoulent naturellement les questions d'echange, de reutilisation, d'incrementabilite de ces ressources de traduction. L'investissement associe (tant d'un point de vue prive que public), a conduit a une tendance generale pour l'etablissement d'initiatives de centralisation (cf Elra), de normes (ISO 12220), de formalismes de transfert (OLIF), ou de maniere plus generale, de formats d'echange d'information multilingue (UNL). Dans tous les cas, le choix du support de l'information linguistique ne peut etre dissocie de considerations pragmatiques d'echelle, le volume des ressources additionnelles devenant plus important que celui des ressources generiques. Ces ressources pouvant aller de ressources terminologiques "simples" (dictionnaires alignes), a des ressources plus complexes comme des grammaires terminologiques, dictionnaires de transfert, et graphes/grammaires de traduction. CENTRES D'INTERET DE L'ATELIER Les centres d'interet de l'atelier concernent non seulement la recherche en traduction automatique et les produits, mais egalement les developpements multilingues recents en TAL. Cet atelier vise a developper une reflexion autour des questions de constitution, de validation, et d'utilisation de ressources a large couverture en traduction automatique. Les articles proposes pourront en particulier aborder les points suivants, mais aussi tout probleme connexe : - utilisation de formalismes de normalisation sur des grands volumes de donnees - evaluation et realisation d'outils de construction de telles ressources (a partir de corpus, de ressources monolingues...) - integration et conversion de ressources existantes - validation et processus d'enrichissement "expertise" - acquisition parallele massive de terminologie dans le cadre d'un reseau d'utilisateurs - gestion de ressources multilingues comparees a celles de ressources bilingues - extraction multilingue et traduction automatique PRECISIONS Vous pouvez soit soumettre un resume de 5 pages, soit une version complete de votre article (jusqu'a 10 pages). Les articles soumis doivent etre ecrits en francais ou en anglais (pour les non-francophones). Les resumes et les articles doivent correspondre au format de TALN'2001 (des feuilles de style sont disponibles sur le site de TALN'2001 http://www.li.univ-tours.fr/taln-recital-2001) : Times 12, interligne simple, 10 pages au maximum, figures, exemples et references comprises. Les auteurs enverront leur resume ou leur article en fichier attache (ps, pdf, rtf au format A4) a l'adresse email suivante : workshop-taln at systran.org L'email contiendra les informations suivantes : titre de la soumission, nom de l'auteur, affiliation. Les resumes et articles soumis seront evalues par deux experts du Comite de Programme. La version finale des articles acceptes sera publiee dans les actes de l'Atelier. Les communications donneront lieu a une presentation de 20 minutes et seront suivies de 10 minutes de questions. COMITE DE PROGRAMME Christian Boitet, CLIPS-IMAG,equipe GETA, Grenoble http://clips.imag.fr/geta Maurice Gross, LADL & UMLV, Marne-la-Vallee Igor Boguslavskij, IPPI PAN, Moscou Georges Carayannis, ELRA & ILSP, Athen Joseph Dichy, Faculte des Langues, Universite Lyon II Pierre-Yves Foucou, SYSTRAN, Paris http://www.systransoft.com Daniel Grasmick, SAP, Waldorf Jean Senellart, SYSTRAN, Paris http://www.systransoft.com Tamas Varadi, Linguistics Institute, Hungarian Academy of Sciences Remi Zajac, CRL/NMSU, Las Cruces, http://crl.nmsu/edu/~rzajac Date limite de soumission : 15/04/2001 Notification aux auteurs : 25/04/2001 Version finale (prete a la reproduction) : 15/05/2001 Atelier : 5 juillet 2001 ___________________________________________________________________ Message diffus� par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Mon Feb 12 17:21:58 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Mon, 12 Feb 2001 18:21:58 +0100 Subject: Publications: Revue de semantique et pragmatique Message-ID: From: "Francois NEMO" Revue de Semantique et Pragmatique ISSN 1285-4093 Numero 8, 2000 http://www.univ-orleans.fr/PUO/RSP/ TITRE: Imperatif, indicatif et subjonctif : de la morphologie a l'interaction AUTEUR(S): Daniel Luzzati PAGE(S): 7-27 TITRE: Pour une approche linguistique ET discursive de l'organisation informationnelle AUTEUR(S): Anne Grobet PAGE(S): 29-42 TITRE: A propos de quelques actes ``pseudo-directifs'' de la communication ecrite AUTEUR(S): Giuseppe Manno PAGE(S): 43-62 TITRE: Par terre vs sur le sol AUTEUR(S): S.-N. Kwon-Pak PAGE(S): 63-79 TITRE: Discourse particles, turn-taking, and the semantics-pragmatics interface AUTEUR(S): Kerstin Fischer PAGE(S): 81-100 TITRE: Le fonctionnement de la conjonction mais dans le dialogue romanesque AUTEUR(S): Isabelle Daussaint-Doneux PAGE(S): 101-119 TITRE: Temporality and causality: The case of Greek subordinating connectives AUTEUR(S): Eliza Kitis PAGE(S): 121-141 TITRE: Adverbes iteratifs et quantification AUTEUR(S): Francis Renaud PAGE(S): 143-168 Compte rendu TITRES: 1) Une histoire du point de vue 2) La construction textuelle du point de vue AUTEUR: Alain Rabatel Lecteur: Eric Beaumatin Merci d'excuser les doubles envois ___________________________________________________________________ Message diffus� par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Mon Feb 12 17:22:32 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Mon, 12 Feb 2001 18:22:32 +0100 Subject: Appel: TALN 2001 Message-ID: ********************************************************************** * * TALN 2001 * Traitement Automatique du Langage Naturel * * Universite de Tours * du lundi 2 au jeudi 5 juillet 2001 * * http://www.li.univ-tours.fr/taln-recital-2001/ * mailto::taln2001 at univ-tours.fr * ********************************************************************** (see English version below) ********** TALN 2001 : 3eme APPEL A COMMUNICATION ********** ----> DATE LIMITE DE SOUMISSION : VENDREDI 23 FEVRIER 2001 <---- TALN 2001 aura lieu a Tours du lundi 2 au jeudi 5 juillet 2001, organise par le LI (Laboratoire d'Informatique de l'Université de Tours) et l'axe LTI (Langues et Technologies de l'information). La conference TALN 2001 comprendra des communications scientifiques, des conferenciers invites, des seances de demonstration et posters, ainsi que des tutoriels. Les langues officielles de la conference sont le francais et l'anglais. TALN 2001 est organisee sous l'egide de l'ATALA (Association pour le Traitement Automatique des LAngues) et se tiendra conjointement a la conference pour jeunes chercheurs RECITAL 2001 (appel a communications a paraitre separement). ********** THEMES ********** Les communications pourront porter sur tous les themes habituels du TALN, incluant, de facon non limitative: lexique morphologie syntaxe semantique pragmatique discours analyse generation resume dialogue traduction automatique approches logiques, symboliques et statistiques TALN 2001 souhaite egalement accueillir des travaux de domaines proches dans lesquels le TALN joue un role important, dans la mesure ou l'accent est mis sur la composante TALN : traitement de la parole (prosodie, linguistique, pragmatique) traitement de l'ecrit aspects cognitifs terminologie acquisition de connaissances a partir de textes extraction d'information recherche documentaire linguistique de corpus linguistique mathematique utilisation d'outils de TALN pour la modelisation linguistique enseignement assiste, enseignement des langues. Sont aussi attendus des travaux sur des applications du TALN, implementees et evaluees, faisant ressortir leurs aspects scientifiques et les enseignements tires. Des demonstrations de systemes pourront etre proposees, independamment ou en complement d'articles scientifiques. L'emploi du temps de la conference comprendra une session pour ces demonstrations. ********** CALENDRIER ********** ----> DATE LIMITE DE SOUMISSION : VENDREDI 23 FEVRIER 2001 <---- Notification aux auteurs : vendredi 27 avril 2001 Version finale (pret-a-clicher) : vendredi 11 mai 2001 Conference : du lundi 2 au jeudi 5 juillet 2001 ********** MODALITES DE SOUMISSION ********** Les articles soumis seront rediges en francais (ou en anglais par les non-francophones). Ils ne devront pas depasser 10 pages en Times 12, espacement simple, figures, exemples et references compris. Les soumissions devront parvenir au comite d'organisation avant le 23 fevrier 2001, sous forme electronique, a mailto:taln2001 at univ-tours.fr. En cas d'impossibilite d'envoi par courrier electronique, une soumission "papier" pourra etre admise. Dans ce cas, trois exemplaires devront etre envoyes a l'adresse suivante: TALN 2001 LI (Laboratoire d'Informatique de l'Universite de Tours) E3i, 64, avenue Jean Portalis 37200 Tours France ********** FORMAT DES SOUMISSIONS ********** Les auteurs devront envoyer leur soumission par courrier electronique sous la forme d'un document attache (fichiers ps ou pdf au format A4 et non Lettre US). Le message contiendra le titre de la soumission et les noms des auteurs. Les formats a utiliser pour la redaction sont disponibles sur le site de la conference: http://www.li.univ-tours.fr/taln-recital-2001. ********** CRITERES DE SELECTION ********** Les auteurs sont invites a soumettre des travaux de recherche originaux, n'ayant pas fait l'objet de publications anterieures. Les soumissions seront examinees par au moins deux specialistes du domaine. Seront considerees en particulier : L'importance et l'originalite de la contribution, La correction du contenu scientifique et technique, La discussion critique des resultats, en particulier par rapport aux autres travaux du domaine, La situation des travaux dans le contexte de la recherche internationale, L'organisation et la clarte de la presentation, L'adequation aux themes de la conference. Les articles selectionnes seront publies dans les actes de la conference. ********** DEMONSTRATIONS ET POSTERS ********** Une ou deux seances specifiques seront prevues pour des demonstrations (presentations logicielles) et des posters (85 x 120 cm). Les propositions de demonstration ou de poster suivent les memes regles que les soumissions de communication mais ne devront pas depasser 4 pages. ********** PRESENTATIONS ORALES ********** Les presentations orales dureront 20 minutes et seront suivies de 10 minutes de questions. Il sera possible d'utiliser un retro-projecteur ou un video-projecteur. ********** ACTES ********** Les actes de la conference seront distribues a tous les participants. Le Comite de redaction de la revue Traitement Automatique des Langues (t.a.l.) sélectionnera deux articles pour publication. ********************************************************************** * * ENGLISH VERSION * ********************************************************************** ********** TALN 2001 : 3rd CALL FOR PAPERS ********** ----> SUBMISSION DEADLINE: FRIDAY, 2/23/2001 <---- TALN 2001 will be held at Tours on July, 2 - 5 2001, organized by the LI (Computer Laboratory of Tours University) and LTI (Language and Information Technologies). The conference includes paper presentations, invited speakers, tutorials and software demonstrations. The official conference languages are French and English. TALN 2001 is organized in collaboration with ATALA (Association pour le Traitement Automatique des LAngues) and will be held jointly with the young researcher conference RECITAL 2001 (a separate call for papers will follow). ********** TOPICS ********** Papers are invited in all areas of NLP, including (but not limited to): lexicon morphology syntax semantics pragmatics discourse parsing generation abstraction/summarisation dialogue translation logical, symbolical and statistical approaches TALN 2001 also invites contributions in fields for which NLP plays an important role, as long as these contributions emphasize their NLP dimension : speech processing text processing cognition terminology knowledge acquisition information retrieval documentary research corpus-based linguistics mathematical linguistics management and acquisition of linguistic resources computer assisted learning NLP tools for linguistic modelization TALN 2001 also welcomes submissions focusing on NLP applications that have been implemented, tested and evaluated and emphasizing the scientific aspects and conclusions drawn. Software demonstrations can be proposed, either independently or in connection with a paper proposal. Specific sessions for the demos will be scheduled in the conference. ********** CALENDAR ********** ----> SUBMISSION DEADLINE: FRIDAY, 2/23/2001 <---- Notification to authors: 4/27/2001 Final version due (camera-ready): 5/11/2001 Conference : 7/2-5/2001 ********** SUBMISSION PROCEDURE ********** The maximum length for papers is 10 pages, in Times 12, single spaced, including figures, examples and references. Electronic submissions must reach the organizing committee before 2/23/2001, sent to mailto:taln2001 at univ-tours.fr. If electronic submission is not possible, 3 hard-copies of the paper must reach the organizing committee before 2/23/2001, at the following address: TALN 2001 LI (Laboratoire d'Informatique de l'Universite de Tours) E3i, 64, avenue Jean Portalis 37200 Tours France ********** FORMAT FOR SUBMISSIONS ********** Authors should send their submission as a file attached to an e-mail(ps or pdf files, A4 format and not US Letter format), containing the following informations: submission title and author's names. The formats that MUST be used are available on the Conference web site: http://www.li.univ-tours.fr/taln-recital-2001/ . ********** SELECTION CRITERIA ********** Authors are invited to submit original, previously unpublished work. Submissions will be reviewed by at least 2 specialists of the domain. Decisions will be based on the following criteria : Importance and originality of the paper Accuracy of the scientific and technical content Comparison of the results obtained with other relevant work Layout and clarity of the paper Relevance to the topics of the conference Accepted papers will be published in the proceedings of the conference. ********** DEMOS AND POSTERS ********** One or two specific sessions for the demos and the posters (85 x 120 cm) will be scheduled in the conference. The demo or poster submissions accord to the same rules of paper submission, BUT they should not exceed 4 pages. ********** TALKS ********** Papers should be of 20 minutes duration. 10 minutes will be left for questions. It will be possible to use a overhead projector or a video-projector. ********** PROCEEDINGS ********** The conference proceedings will be given to all participants. The editorial staff of the journal Traitement Automatique des Langues (t.a.l.) will select two papers for publication. ********** COMITE DE PROGRAMME ********** ********** PROGRAMME COMMITTEE ********** (le comite de programme sera entoure d'un large comite de lecture) (the program committee will be supervised by a broad reviewing committee) Pascal Amsili, TALaNa Frederic Bechet, LIA Philippe Blache, LPL Christian Boitet, CLIPS-GETA Pierrette Bouillon, ISSCO Beatrice Daille, IRIN Laurence Danlos, LORIA/TALaNa Claire Gardent, LORIA Eric Laporte, CERIL Denis Maurel, LI (president) Piet Mertens, CCL Jean-Marie Pierrel, LORIA Martin Rajman, EPFL Owen Rambow, ATT Labs-Research Jacques Siroux, IRISA LLI/CORDIAL Jean Veronis, LPL Pierre Zweigenbaum, DIAM ********** COMITE D'ORGANISATION ********** ********** ORGANIZING COMMITTEE ********** Claire Agafonov, LTI Beatrice Bouchou, LI Alain Cambourian, LTI Alain Delplanque, LTI Nathalie Friburger, LI Nathalie Garric, LTI Paul Gaudin, LTI Manuel Gonzales de Avila, Ciremia Thierry Grass, LTI Denis Maurel, LI (president) Nathalie Rossi, LTI Mohamed Slimane, LI Nicole Vincent, LI ___________________________________________________________________ Message diffusé par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Thu Feb 15 17:45:55 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Thu, 15 Feb 2001 18:45:55 +0100 Subject: Jobs: 4 offres Message-ID: 1/ From: Mari Olsen Subject: Jobs: Microsoft Natural Language Group 2/ From: Joanne Samuelson Subject: Wordstream, Inc. career opportunity 3/ From: Jean Pierre Chanod Subject: 2 postes de chercheur en sémantique; 2 research positions in semantics: 4/ From: Jean Pierre Chanod Subject: Post-Doc - MultiLingual Theory and Technologies ------------------------------------------------------------------------------ 1/ From: Mari Olsen Subject: Jobs: Microsoft Natural Language Group Send applications/questions to nljobs at microsoft.com. -Mari Broman Olsen Computational Linguist - French Primary responsibilities include enhancing and extending the French computational grammar and grammar-checking system, in accordance with the overall architecture of the Microsoft Natural Language Understanding system. The initial emphasis will be on understanding the output of the syntactic component. Native French language proficiency and an advanced degree in Linguistics, Computer Science, or a closely related discipline are required. Other desirable qualifications include experience in linguistic research, with an emphasis on syntax, semantics, or discourse analysis; familiarity with Natural Language Processing; a flexible approach to linguistic theory; practical experience with software development and NLP implementation issues. Linguistic Test Engineer - Spanish Primary responsibility is the creation and maintenance of linguistic test data for Microsoft's Spanish Natural Language Processing system. Responsibilities include analyzing a corpus in Spanish and creating expected linguistic output based on a specification, evaluating linguistic coverage, reporting accuracy, finding and tracking linguistic bugs, and measuring improvement of the products and technology. Native Spanish language proficiency and bachelor's degree in Linguistics or Computational Linguistics required; a master's or doctorate degree strongly preferred. Other qualifications include demonstrated skill in detailed linguistic analysis, with an emphasis on syntax or semantics; general investigative and problem-solving skills; and an ability to track details. General knowledge of personal computers, and the ability to install, upgrade and use Microsoft applications and operating system(s) are desirable. Computational Linguist - Semanticist Enhance, develop, and ship technology in important new problem domains, including information retrieval, information extraction, generation, and natural language command & control of applications, all of which require an integrated understanding of computational semantics. Candidates are welcomed from a broad variety of disciplines and backgrounds, for example, with expertise in any of the following areas: statistical approaches to problems like word sense disambiguation or word correlation; knowledge-based techniques involving semantic networks or ontologies; computational approaches to "dynamic" semantic theories like DRT, Dynamic Montague Grammar or Context/File Change Semantics; inter alia. Qualified applicants should have an advanced degree in Linguistics, Computational Linguistics, or CS (or equivalent experience), strong coding skills, and a desire to see their ideas through to the product stage. ------------------------------------------------------------------------------ 2/ From: Joanne Samuelson Subject: Wordstream, Inc. career opportunity Director of Language Development, Computational Linguist Opportunity to join an exciting young company with a creative approach to language translation. WordStream isn?t trying to be another Machine Translation company but rather has redefined the problem and is solving it with a unique technology based on an Interlingua. Competitive salary and benefits. Metropolitan Boston location. Job Description: Computational linguist to lead development and design of commercial interlingua MT system and to manage a team of linguists. The job will involve determining the conceptual framework for the development of a lexical database and grammar system. Candidate will need to work closely with Software Development team to ensure coordination of linguistic and technical requirements. Job Requirements: Master?s (PhD preferred) in Computational Linguistics or related areas. Fluent in English and at least one other language, preferably one of the following: German, French, Spanish, Italian, Japanese or Chinese. Excellent communication skills as well as the ability to both motivate a team and be a team player. Highly Desirable: Experience with commercial MT systems along with project management and implementation of MT applications. Experience managing linguists and technology specialists. Familiarity with linguistic resources (corpora, grammars, parsers, etc.). Programming skills (knowledge of perl, java, or C++). Experience in grammar and lexicon development. Interested parties should contact : www.wordstream.com careers at wordstream.com WordStream Inc. 48 Grove St. Suite 201 Somerville MA 02144 Tel 617-666-7700 X231 Fax 617-666-2850 ------------------------------------------------------------------------------ 3/ From: Jean Pierre Chanod Subject: 2 postes de chercheur en sémantique; 2 research positions in semantics: XRCE-Grenoble (Xerox Research Centre Europe) est spécialisé dans la recherche en traitement automatique des langues, en systèmes distribués, et en gestion de la connaissance. Ce laboratoire travaille en association étroite avec les autres laboratoires de Xerox à Cambridge et Palo Alto (PARC). MLTT (the MultiLingual Theory and Technology Group) a deux postes à pourvoir pour des chercheurs dans le domaine du traitement sémantique de textes. En collaboration avec le groupe de recherche, les candidats devront conduire des recherches et développer des méthodes pour représenter le contenu sémantique des textes, fusionner ces contenus avec des informations externes (telles que des ontologies), et enfin effectuer des raisonnements sur les représentations ainsi générées. Ces techniques seront appliquées à des tâches telles que l'extraction de connaissance sur des textes tout venant. Qualifications: Les candidats devront avoir un doctorat ou équivalent dans l'une des disciplines suivantes: linguistique, mathématique, informatique. Une expérience en traitement automatique des langues est souhaitable. La maîtrise de la langue anglaise, parlée et écrite, est requise. XRCE offre d'excellents salaires ainsi que divers avantages sociaux, un bon environnement informatique et la possibilité de travailler pour un centre international de recherche leader dans son domaine. Le lieu de travail est situé à Grenoble (France), au pied des Alpes (snowboard, ski, golf, randonnée, kayak, parapente, escalade, pêche etc.). Les pages WEB (http://www.xrce.xerox.com) sont à votre disposition pour de plus amples informations sur le centre. Les postes sont à durée indéterminée, et ouverts dès maintenant. Les candidatures dans le cadre d'un sabbatique sont également les bienvenues. Les demandes devront inclure la référence MLTT010207 et devront être envoyées à l'adresse suivante: Mr. Christophe Mitenne Ressources Humaines Xerox Research Centre Europe 6, chemin de Maupertuis 38240 MEYLAN, France English version: XRCE Grenoble Laboratory is a world leader in natural language, distributed systems, and knowledge management research. It forms an integral part of Xerox's research culture with sister laboratories in Cambridge (UK) and Palo Alto (PARC, California). The MultiLingual Theory and Technology Group has two open positions for researchers in semantic processing of natural language texts. In collaboration with a group of researchers, the candidates will investigate and elaborate state-of-the-art techniques for representing the contents of natural language texts, for merging these contents with background information (such as ontologies) and for performing some reasoning on the basis of such representations. The resulting techniques will be applied to tasks such as knowledge extraction from unrestricted texts. Research Focus & Qualifications: Applicants should hold a Ph.D. degree or equivalent in a relevant discipline e.g. computer science, linguistics, mathematics etc. Hands-on experience with applying a wide range of NLP techniques is also desirable. Proficiency in English is required. XRCE offers excellent salaries and benefits (and relocation package), excellent computing facilities and the opportunity to work in a leading international research institute. The successful candidates will be located in Grenoble (France), in the foothills of the Alps, providing access to some of the best outdoors in the world (activities in this region include: snowboarding, skiing, golfing, hiking, kayaking, paragliding, rock climbing, fishing etc.). Please refer to the XRCE webpages (http://www.xrce.xerox.com) for further information regarding this position and on our research centre. The positions are permanent and are open now. Applications for sabbaticals are also welcomed. Applications should include the reference MLTT010207 and should be sent to following address: Mr. Christophe Mitenne Human Resources Xerox Research Centre Europe 6, chemin de Maupertuis 38240 MEYLAN, France -------------------------------------------------------------------------- 4/ From: Jean Pierre Chanod Subject: Post-Doc - MultiLingual Theory and Technologies Ref: MLTT/010208 XRCE Grenoble Laboratory is a world leader in natural language, distributed systems, and knowledge management research. It forms an integral part of Xerox's research culture with sister laboratories in Cambridge (UK) and Palo Alto (PARC, California). The MultiLingual Theory and Technology Group has an open position for a post-doc, for a duration 18 months, starting in May 2001. In collaboration with a small group of other researchers, the candidate will elaborate state-of-the-art robust language components for English, based on our new system for text analysis and on existing language resources. The primary focus is on expanding our English dependency grammar, with a view of applying it to higher-level linguistic processes (coreference, word sense & structural disambiguation,s paraphrase, mapping onto knowledge representation). Those linguistic components will be used and tested in a number of large-scale applications, such as knowledge extraction in genomics. Research Focus & Qualifications: Applicants should hold a Ph.D. degree or equivalent in a relevant discipline e.g. computer science, linguistics, mathematics etc. Hands-on experience with applying NLP techniques to real texts is a must.The candidate should be a native speaker of English. XRCE offers competitive salaries, excellent computing facilities and the opportunity to work in a leading industry-geared research institute. The successful candidate will be located in Grenoble (France), in the foothills of the Alps, providing access to some of the best outdoors in the world (activities in this region include: snowboarding, skiing, golfing, hiking, kayaking, paragliding, rock climbing, fishing etc.). Please refer to the XRCE webpages (http://www.xrce.xerox.com) for further information regarding this position and on our research centre Applications should include the reference MLTT010208 and should be sent to following address: Mr. Christophe Mitenne Human Resources Xerox Research Centre Europe 6, chemin de Maupertuis 38240 MEYLAN, France ___________________________________________________________________ Message diffusé par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Thu Feb 15 17:46:10 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Thu, 15 Feb 2001 18:46:10 +0100 Subject: Ecole: MASTER - UNIVERSITY OF CAMBRIDGE Message-ID: *** ONE YEAR GRADUATE COURSE *** ** STUDENTSHIPS AVAILABLE ** ------------------------------------------------------------------------ COMPUTER SPEECH, TEXT, AND INTERNET TECHNOLOGY ONE YEAR MASTERS COURSE THE DEPARTMENT OF ENGINEERING AND THE COMPUTER LABORATORY UNIVERSITY OF CAMBRIDGE ------------------------------------------------------------------------ This new Masters course replaces the highly successful M.Phil in Computer Speech and Language Processing. Like its predecessor, a key aim of the new Masters course in Computer Speech, Text and Internet Technology is to teach the fundamental theory of speech and natural language processing. However, the new course also focuses on its application to information management and access within the framework of emerging Internet and W3C standards, such as XML text and speech annotation and 3G wireless communication. It runs from early October to August and consists of two terms of lectures and practicals followed by a three month project. The final degree is awarded on the basis of coursework, examination and project. The course differs from some other programmes by providing an in-depth practical and theoretical grounding in the techniques for speech and language processing which form the basis for today's commercial and research prototype systems. There are strong links with industry and many of our past students have gone on to work for high-tech start-ups and industrial research laboratories, either immediately or after completing a PhD. To further strengthen our links with industry, we are making this course available to students wishing to pursue it on a part-time basis. Cambridge is a major international centre for research in both speech and language processing. The course is taught by leading researchers in these areas who have active collaborations with industrial and academic laboratories in Europe, the US and Japan. The EPSRC have funded a number of studentships for the course which are currently available to qualifying applicants. We especially encourage applications from students with a background in engineering, computer science, mathematics, linguistics and/or psychology. For further details please consult the course URL: http://svr-www.eng.cam.ac.uk/cstit/ or contact: Mrs Mavis Barber (Computer Speech, Text, and Internet Technology) Department of Engineering, University of Cambridge Trumpington Street, Cambridge CB2 1PZ, UK Tel: +44-1223-332752 Fax: +44-1223-332662 Email: mavis at eng.cam.ac.uk ------------------------------------------------------------------------ ___________________________________________________________________ Message diffus� par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Thu Feb 15 17:46:25 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Thu, 15 Feb 2001 18:46:25 +0100 Subject: Appel: GL2001 Message-ID: =========================================================================== GL2001 GL2001 GL2001 GL2001 GL2001 GL2001 GL2001 GL2001 GL2001 GL2001 GL2001 1st International Workshop on Generative Approaches to the Lexicon =========================================================================== First call for participation April 26-28 2001 University of Geneva (Switzerland) http://issco-www.unige.ch/gl2001.html ---------------------------------------------------------------------------- - TOPIC The aim of this workshop is to bring together diverse contributions in philosophy, linguistics, computer science and lexicography to explore the lexicon from the point of view of generativity. The discussions will be centered, but are not limited to, the newly emerging view of Generative Lexicon Theory (Pustejovky, 1995). Topics include: - Philosophical Foundations of a Generative Approach - Representation of Word Meaning - Generative Lexicon Theory - Analysis of Linguistic Phenomena - Building Lexical Resources - Exploiting Lexical Resources in NLP Applications - Lexical Rules - Framework for Lexical Semantics - Critical Perspectives PROGRAM The program will include: - A SPECIAL TALK by James Pustejovsky (Brandeis University, Boston) - INVITED TALKS by Nicolletta Calzolari (Istituto Di Linguistica Computazionale, Pisa) Ann Copestake (Cambridge University, Cambridge) Hitoshi Isahara (Communications Research Laboratories, Kyoto) Evelyne Viegas (Microsoft, Natural Language Group, Redmond) Piek Vossen (Sail-labs, Antwerpen) Yorick Wilks (University of Sheffield, Sheffield) - 21 oral presentations (long (30 min) and short (20 min)) GL2001 is: - founded by the Swiss National Science Foundation (FNRS) and the Communications Research Laboratory (Kyoto) - hosted by University of Geneva, ISSCO/TIM. Organizers: Pierrette Bouillon (ISSCO/TIM, University of Geneva, Geneva) Kyoko Kanzaki (Communications Research Laboratory, Kyoto) The GL2001 program and registration form are now available at: http://issco-www.unige.ch/gl2001.html =========================================================================== GL2001 GL2001 GL2001 GL2001 GL2001 GL2001 GL2001 GL2001 GL2001 GL2001 GL2001 =========================================================================== ___________________________________________________________________ Message diffus� par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Thu Feb 15 17:46:39 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Thu, 15 Feb 2001 18:46:39 +0100 Subject: Appel: DCAGRS_01 Message-ID: From: Bernd Reichel Dear Colleague, This is to inform you about the Third Workshop "Descriptional Complexity of Automata, Grammars and Related Structures" which will be held at the Technical University of Vienna (in conjunction with the Fifth International Conference on Developments in Language Theory). The goal of the workshop is to present the state of the art and to provide a forum for the exchange of new results. The Call for Papers and further information you can find at http://theo.cs.uni-magdeburg.de/dcagrs01/ Yours sincerely, Bernd Reichel ************************************************************************ Dr. Bernd Reichel Gebaeude 18 Raum 232 Fakult"at f"ur Informatik Tel.: +49-391-67-12851 Otto-von-Guericke-Universit"at Fax: +49-391-67-11250 Postfach 4120 reichel at iws.cs.uni-magdeburg.de 39016 Magdeburg http://theo.cs.uni-magdeburg.de/~reichel ************************************************************************ ___________________________________________________________________ Message diffus� par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Thu Feb 15 17:46:59 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Thu, 15 Feb 2001 18:46:59 +0100 Subject: Appel: 4th INTEX Workshop Message-ID: French version below: 4th INTEX Workshop University of Bordeaux-3, June 11th and 12th juin, 2001 INTEX is a linguistic development environment that allows users to construct large-coverage linguistic resources, and to apply them to large texts. These resources can be DELA-type dictionaries, libraries of finite-state graphs and syntactic & semantic data bases in the form of lexicon-grammars. One characteristic of the system is that it is open: users can add their own linguistic resources and use elementary functionalities in their own applications, either by importing standalone programs, or by using the API. INTEX is used in more than 60 research centers as a linguistic tool, an information retrieval system, to teach second languages, as a terminological extractor, as well as to teach computational linguistics to graduate students. This fourth workshop will offer the INTEX users the opportunity to meet and share their experience in research, development and teaching. The latest additions to the features of INTEX will be presented. For the new INTEX users, or for researchers who use other linguistic development environments, the workshop will be an opportunity to discover a wide spectrum of projects that are based on the INTEX technology. Following the presentations, two tutorial sessions (initiation, advanced) will give participants an opportunity to play with the system. Submission process: By March 15th, 2001, submit a 1-page abstract to Claude Muller or Max Silberztein, using e-mail preferably. The title of the abstract should include: title of the paper, name, affiliation, postal address, e-mail address for each author. Authors will be notified of acceptance by April 15th. Contacts : Claude Muller UFR Lettres, Université de Bordeaux-3, Domaine Universitaire, 33607 PESSAC CEDEX (FRANCE). fax: +33(0)557 12 45 29 email: muller at montaigne.u-bordeaux.fr Max Silberztein IBM T.J. Watson Research Center 30 Sawmill River Road Hawthorne, NY 10532, USA fax: 1 (914) 784-6307 email: ms1 at us.ibm.com #-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#- 4èmes Journées INTEX Université de Bordeaux-3, les 11 et 12 juin 2001 INTEX est une plate-forme d'ingénierie linguistique permettant de développer des ressources linguistiques à large couverture et de les appliquer à des textes de taille importante. Ces ressources peuvent prendre la forme de dictionnaires électroniques au format DELA, bibliothèques de graphes à états finis et bases de données syntactico-sémantiques du type lexique-grammaire. L'une des particularités du système est son ouverture : les utilisateurs peuvent ajouter leurs propres ressources et réutiliser les fonctionnalités élémentaires du système dans leurs propres applications, soit à partir de programmes individuels, soit à partir de l'API. INTEX est utilisé dans plus de 60 centres de recherche universitaires ou privés comme outil de développement linguistique, moteur de recherche, aide à l'enseignement des langues, outil d'extraction terminologique, et pour enseigner l'informatique linguistique. Comme les trois premières éditions (juin 1996, juin 1999, juin 2000), ces journées seront l'occasion pour les utilisateurs d'INTEX de se rencontrer et d'échanger leur expérience de développeur, de chercheur ou d'enseignant. Elles seront également l'occasion de présenter les nouvelles fonctionnalités d'INTEX issues des récents développements. Pour les nouveaux utilisateurs ou les chercheurs travaillant avec d'autres systèmes, ces journées offrent la possibilité de découvrir un panel diversifié de domaines d'application d'INTEX. En plus des communications portant sur des recherches ou développements en cours, deux tutoriels (initiation, avancé) permettront d'expérimenter concrètement le logiciel. Dates importantes: Veuillez envoyer un resume d'une page avant le 15 mars 2001 a Claude Muller ou Max Silberztein, par e-mail si possible. Le titre du resume doit contenir le titre de la presentation, la nom, l'affiliation, l'adresse postale et electronique de chaque auteur. Contacts : Claude Muller UFR Lettres, Université de Bordeaux-3, Domaine Universitaire, 33607 PESSAC CEDEX (FRANCE). fax: +33(0)557 12 45 29 email: muller at montaigne.u-bordeaux.fr Max Silberztein IBM T.J. Watson Research Center 30 Sawmill River Road Hawthorne, NY 10532, USA fax: 1 (914) 784-6307 email: ms1 at us.ibm.com ___________________________________________________________________ Message diffusé par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Thu Feb 15 17:47:20 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Thu, 15 Feb 2001 18:47:20 +0100 Subject: Appel: EUROLAN 2001 WORKSHOP Message-ID: ******* EUROLAN 2001 WORKSHOP ******* MULTI-LAYER CORPUS-BASED ANALYSIS July 30 - August 1, 2001 Iasi, Romania http://www.cs.vassar.edu/~ide/Eurolan01-ws.html Organizers: Dan Cristea, University "A.I. Cuza", Iasi, Romania Nancy Ide, Vassar College, USA Daniel Marcu, ISI, University of Southern California Massimo Poesio, University of Edinburgh Corpora annotated for a variety of linguistic features are becoming increasingly available. Part of speech annotated corpora are commonplace; treebanks in a variety of languages are available or under development; and corpora annotated for various features of discourse, including co-reference and discourse structure, are also available (e.g., the MUC corpora). In addition, large speech corpora annotated with phonetic transcriptions and prosodic analysis and various multi-lingual aligned corpora are available from centers such as the Linguistic Data Consortium and the European Language Resources Association. This workshop will address issues of using corpora annotated for multiple layers (e.g., syntax and discourse, prosody and part of speech, etc.) or combining multiple layers of annotation in natural language analysis. We invite submissions on the following topics: o Research that exploits information on different linguistic levels; o Consideration and demonstration of the ways in which information from different layers can be used in automatic language processing; o Compatibility of corpora annotated for different linguistic layers, including means to harmonize different annotation types and levels; o Tools for exploiting different levels of annotation. The workshop will be held over three consecutive evenings in conjunction with the EUROLAN 2001 Summer School on Creation and Exploitation of Annotated Language Resources, in Iasi, Romania. Because EUROLAN 2001 is concerned with a wide variety of types of linguistic annotation, the workshop will serve to complement the content of lectures and tutorials that are part of the School's main program. Registration for the workshop is included in the Summer School registration fee. Information on EUROLAN 2001 is available at http://www.infoiasi.ro/~eurolan2001/ and http://www.clg.wlv.ac.uk/eurolan/ SUBMISSION INFORMATION: Papers should report on original work not previously presented elsewhere. The workshop is intended to provide a forum for discussion and a means to receive feedback for future development; therefore, papers describing both completed work and work-in-progress are acceptable. Submissions of 3500-5000 words should be sent via email to ide at cs.vassar.edu with the subject line "EUROLAN 2001 WORKSHOP SUBMISSION". Submissions in Postscript, PDF, or plain ASCII text formats are acceptable. DATES: Deadline for receipt of submissions : April 15, 2001 Notification of acceptance : May 1, 2001 Final Paper due : June 1, 2001 Workshop date : July 30 - August 1, 2001 PROGRAM COMMITTEE (tentative): Paul Buitelaar - DFKI, Saarbrucken Graeme Hirst - University of Toronto Eduard Hovy - University of Southern California Adam Kilgarriff - University of Brighton Ruslan Mitkov - University of Wolverhampton Sergei Nirenburg - New Mexico State University Laurent Romary - LORIA Nancy Dan Tufis - Romanian Academy Hans Uszkoreit - Saarland University of Saarbrucken Piek Vossen - Sail-labs, Antwerp-Berchem Yorick Wilks - University of Sheffield ___________________________________________________________________ Message diffus� par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Thu Feb 15 17:48:43 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Thu, 15 Feb 2001 18:48:43 +0100 Subject: Publications: T.A.L. JOURNAL: SPECIAL ISSUE IN IR-ORIENTED NLP Message-ID: +-----------------------------------------------+ I T.A.L. journal I I (Le traitement automatique des langues) I I I I http://www.atala.org/tal/tal.html I +-----------------------------------------------+ SPECIAL ISSUE IN "INFORMATION RETRIEVAL-ORIENTED NATURAL LANGUAGE PROCESSING" Vol. 41, Num. 2, January 2001 -------------- Table of contents Christian JACQUEMIN : Présentation du numéro sur le traitement automatique des langues pour la recherche d'information Patrice BELLOT, Marc EL-BÈZE : Classification locale non supervisée pour la recherche documentaire Pierrette BOUILLON, Cécile FABRE, Pascale SÉBILLOT, Laurence JACQMIN : Apprentissage de ressources lexicales pour l'extension de requêtes Béatrice DAILLE, Jean ROYAUTÉ, Xavier POLANCO : Évaluation d'une plate-forme d'indexation de termes complexes Georgette DAL, Fiammetta NAMER : Génération et analyse automatiques de ressources lexicales construites utilisables en recherche d'informations Gael Harry DIAS, Sylvie GUILLORÉ, Jean-Claude BASSANO, José Gabriel PEREIRA LOPES : Extraction automatique d'unités lexicales complexes : Un enjeu fondamental pour la recherche documentaire Éric GAUSSIER, Gregory GREFENSTETTE, David HULL, Claude ROUX : Recherche d'information en français et traitement automatique des langues Diego MOLLA, Rolf SCHWITTER, Michael HESS and Rachel FOURNIER : EXTRANS, An Answer Extraction System Fiammetta NAMER : FLEMM : Un analyseur flexionnel du français à base de règles Martin RAJMAN, Romaric BESANCON, Jean-Cédric CHAPPELIER : Le modèle DSIR: Une approche à base de sémantique distributionnelle pour la recherche documentaire -------------- All the members of the French Computational Linguistics Association ATALA receive the T.A.L. journal. To become a member of ATALA: http://www.atala.org/adhesion.html The issue can be ordered from Hermès Sciences: hermes at iway.fr http://www.editions-hermes.fr/ ___________________________________________________________________ Message diffusé par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Thu Feb 15 17:49:05 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Thu, 15 Feb 2001 18:49:05 +0100 Subject: Soft: ELRA News Message-ID: ___________________________________________________________ ELRA European Language Resources Association ELRA News ___________________________________________________________ *** ELRA NEW RESOURCES *** We are happy to announce new resources available via ELRA: - Telephone Speech Resources ELRA-S0094 Czech SpeechDat(E) Database ELRA-S0095 Slovak SpeechDat(E) Database ELRA-S0096 German SpeechDat(II) MDB-1000 Database - Written Corpus ELRA-W0026 PAROLE Irish Corpus A short description of each database is given below. Detailed information can be found on the following Website: http://www.elda.fr/catalog.html _______________________________________ TELEPHONE SPEECH RESOURCES _______________________________________ - ELRA-S0094 Czech SpeechDat(E) Database This database comprises 1052 Czech speakers (526 males, 526 females) recorded over the Czech fixed telephone network. - ELRA-S0095 Slovak SpeechDat(E) Database This database comprises 1000 Slovak speakers (498 males, 502 females) recorded over the Slovak fixed telephone network. - ELRA-S0096 German SpeechDat(II) MDB-1000 This database comprises 1295 German speakers (663 males, 610 females, 22 speakers with gender not specified) recorded over the German mobile telephone network. _______________________________________ WRITTEN CORPUS _______________________________________ ELRA-W0026 PAROLE Irish Corpus This corpus consists of over 8 million words The text is marked-up in accordance with the PAROLE encoding standard. All the files are in SGML format with a detailed header and the body of the text tagged to paragraph level. A subset of the corpus is morpho-syntactically tagged. Included in this distribution is approximately 3,000 manually checked words. ===================================== For further information, please contact: ELRA/ELDA Tel +33 01 43 13 33 33 55-57 rue Brillat-Savarin Fax +33 01 43 13 33 30 F-75013 Paris, France E-mail mapelli at elda.fr or visit our Web site: http//www.icp.grenet.fr/ELRA/home.html or http//www.elda.fr ===================================== ___________________________________________________________________ Message diffus� par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Thu Feb 15 17:49:18 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Thu, 15 Feb 2001 18:49:18 +0100 Subject: Conf: IJCAI-01 Text Learning: Beyond Supervision (IJCAI workshop CFP) Message-ID: CALL FOR PAPERS IJCAI-01 Workshop on "Text Learning: Beyond Supervision" Monday, 6 August 2001 Seattle, Washington, USA www.cs.cmu.edu/~mccallum/textbeyond Submission deadline: March 23, 2001 Due to the rapidly increasing amount of textual data available and the range of interesting and important problems arising in text analysis, there has been growing interest in applying machine learning methods to text. There has also been significant recent interest in research that combines supervised and unsupervised learning. This research is especially relevant to text learning because the inherent complexity of natural language usually requires models with many parameters: estimating those parameters requires a lot of data, and obtaining labeled data is difficult and expensive. By combining unsupervised learning with supervised learning, the need for labeled training data can often be greatly reduced, allowing for the development of more powerful models and methods. The workshop will explore machine learning methods for solving supervised text learning tasks that exploit training methods beyond straightforward supervised learning. Relevant topics include: * Text classification with labeled and unlabeled data: EM, co-training, transduction with SVMs, discriminative maximum entropy with unlabeled data. * Information extraction with unlabeled data: bootstrapping, co-boosting. * Part-of-speech tagging, parsing and other NLP with unlabeled data. * Active learning: uncertainty sampling, query-by-committee, version space reduction. * Model selection with unlabeled data. * Word clustering for language modeling, distributional clustering, feature generation by clustering. * Semi-supervised clustering, document clustering with user-feedback. * Integrating prior knowledge into supervised learning, integrating distantly labeled data. * Unsupervised methods for learning segmentation models, translation models, lexicons, etc. * Link analysis for supervised learning. The goal of this workshop is to bring together researchers from the machine learning, information retrieval, computational linguistics and language modeling to talk about their different perspectives and to share their latest ideas. INVITED SPEAKERS ---------------- David Yarowsky Assistant Professor Department of Computer Science Johns Hopkins University http://www.cs.jhu.edu/~yarowsky/ Tommi Jaakkola Assistant Professor Department of Computer Science Massachusetts Institute of Technology http://www.ai.mit.edu/people/tommi/tommi.html SCHEDULE AND SUBMISSION PROCEDURE --------------------------------- Friday, Mar 23 2001 Paper submissions due Friday, Apr 06 2001 Acceptance notification Friday, Apr 20 2001 Camera ready papers due Authors are asked to prepare a paper in Postscript or PDF format. Submissions should conform to the IJCAI-2001 format, and be 8 pages or less. We encourage submissions containing original theoretical and applied concepts. Experimental results are also encouraged, even if they are only preliminary. To submit a paper, email it to textbeyond at whizbang.com before 6pm on the day of the deadline. ORGANIZING COMMITTEE -------------------- Andrew McCallum WhizBang Labs - Research, 4616 Henry Street, Pittsburgh, PA 15218 T: 412-683-9132 F: 412-683-4436 mccallum at whizbang.com http://www.cs.cmu.edu/~mccallum Kamal Nigam School of Computer Science, Carnegie Mellon, Pittsburgh, PA 15213 T: 412-268-3070 F: 412-268-5576 knigam at cs.cmu.edu http://www.cs.cmu.edu/~knigam Tony Jebara MIT, Media Laboratory - 20 Ames Street, E15-390, Cambridge, MA 02138 T: 617-253-0326 F: 617-253-8874 jebara at media.mit.edu http://www.media.mit.edu/~jebara Lillian Lee Department of Computer Science, Cornell University, Ithaca, NY 14853 T: 607-255-8119 F: 607-255-4428 llee at cs.cornell.edu http://www.cs.cornell.edu/home/llee ___________________________________________________________________ Message diffus� par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Tue Feb 20 15:45:48 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Tue, 20 Feb 2001 16:45:48 +0100 Subject: Ecole: Training Workshop in Lexicography and Lexical Computing Message-ID: lexicom at itri A new Training Workshop in Lexicography and Lexical Computing http://www.itri.bton.ac.uk/lexicom The Information Technology Research Institute University of Brighton and The Lexicography MasterClass Brighton, England 16-20 July 2001 Trainers: Sue Atkins, Adam Kilgarriff, Michael Rundell Bringing together lexicographers linguists computer scientists to enable them to develop the skills needed for creating, managing and exploiting lexical data. building and working with text corpora dictionary/lexical databases writing lexical entries (for people and computers) All sessions will include practical work at a computer terminal. The workshop will be tailored to participants' interests; people will be encouraged to bring data from, and explore issues in current projects. For programme see http://www.itri.bton.ac.uk/lexicom/programme.html Location Brighton is a cosmopolitan city by the sea, one hour from London, 30 minutes from London's Gatwick Airport. A brochure and map will be sent to you on receipt of your registration. The workshop will take place on the University of Brighton's Moulsecoomb campus. The campus is 10 minutes by bus from Brighton Sea Front and city centre. There are inexpensive coffee bars and canteens on site. We shall use the IT Faculty Computer Suite which is equipped with over 100 modern PCs. Accommodation University accommodation has been reserved for registrants, in newly built units near the city centre, at a rate of GBP 27.50 per night (including breakfast). A booking form will be sent to you on receipt of your registration, or email conferences at brighton.ac.uk Related events The course will be the week after ACL/EACL in Toulouse, France, two weeks before CogSci in Edinburgh, Scotland, and two weeks after COMPLEX 2001 in Birmingham, England. Fees The registration fee for the course is GBP 600. Second and subsequent participants from the same institution are eligible for a 33% (GBP 200) discount. There is a late registration surcharge of GBP 100 for registrations received after 1st April 2001. Registrations now being accepted. For registration form, go to http://www.itri.bton.ac.uk/lexicom/reg_form.html Trainers: Sue Atkins was General Editor on the Collins-Robert English-French dictionaries and Lexicographic Consultant on the Oxford-Hachette. She is a Founder Member and Past President of Euralex, was the initiator of the British National Corpus and has co-developed the Frame Semantics paradigm with Charles Fillmore. Michael Rundell was Managing Editor of, amongst others the Longman Dictionary of Contemporary English (1987 and 1995 editions), the Longman Lanugage Activator, and the Bloomsbury/Macmillan Dictionary for Learners of English (forthcoming). He has lectured extensively on lexicography and language teaching. Atkins and Rundell have extensive experience of training many teams of lexicographers, for example for the newly-official African languages of South Africa. Adam Kilgarriff has published extensively on lexical computing and the interactions between lexicography and language engineering. He has been a consultant to Longman, Random House, Oxford University Press and Bloomsbury. He is currently President of ACL-SIGLEX. Supported by EURALEX, ELSNET and ACL SIGLEX European Association for Lexicography; European Language and Speech Network; Lexicons Special Interest Group of the Association for Computational Linguistics. http://www.itri.bton.ac.uk/lexicom ___________________________________________________________________ Message diffus� par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Tue Feb 20 15:46:11 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Tue, 20 Feb 2001 16:46:11 +0100 Subject: Conf: Recital 01: extension de la date de soumission Message-ID: (see English version below) *********************************************************************** * * Recital 2001 * -------------------- * Rencontre des etudiants chercheurs en informatique * pour le traitement automatique * des langues * * Attention : extension de la date de soumission * au 6 MARS 2001 * * Universite de Tours * du lundi 2 au jeudi 5 juillet 2001 * * http://www.li.univ-tours.fr/taln-recital-2001/ * mailto:recital2001 at univ-tours.fr ********************************************************************** ********** Recital 2001 : DERNIER APPEL A COMMUNICATION ********** ----> DATE LIMITE DE SOUMISSION (Extension): MARDI 6 MARS 2001 <---- Recital 2001 aura lieu a Tours du lundi 2 au jeudi 5 juillet 2001 en parallele avec la conference TALN 2001 (appel a communications a paraitre separement). La conference Recital 2001 comprendra des communications scientifiques, des conferenciers invites, des seances de demonstration et posters, ainsi que des tutoriels. Les langues officielles de la conference sont le francais et l'anglais. Ces deux conferences sont organisees sous l'egide de l'ATALA (Association pour le Traitement Automatique des LAngues). ********** THEMES ********** Les communications pourront porter sur tous les themes habituels du TALN, incluant, de facon non limitative: Analyse et comprehension de textes Generation d'enonces en langues naturelles Traduction automatique Production de resumes Dialogue homme-machine Recital 2001 souhaite egalement accueillir des travaux de domaines proches dans lesquels le TALN joue un role important, dans la mesure ou l'accent est mis sur la composante TALN : Ressources linguistiques (lexiques, dictionnaires electroniques, corpus, etc.) Semantique lexicale (polysemie, categorisation, etc.) Semantique du temps et de l'espace (representation et raisonnement) Logique (argumentation, modelisation des intentions et des croyances, etc.) Architectures dediees au TAL (systE8mes multi-agents, reseaux neuromimetiques) Acquisition et apprentissage automatique de ressources ou de connaissances (a partir de corpus, ou de l'interaction humain/machine) Relations entre TAL et reconnaissance de la parole ********** CALENDRIER ********** ----> DATE LIMITE DE SOUMISSION : VENDREDI 23 FEVRIER 2001 <---- Notification aux auteurs : vendredi 27 avril 2001 Version finale (pret-a-clicher) : vendredi 11 mai 2001 Conference : du lundi 2 au jeudi 5 juillet 2001 ********** MODALITES DE SOUMISSION ********** Les articles soumis seront rediges en francais (ou en anglais par les non-francophones). Ils ne devront pas depasser 10 pages en Times 12, espacement simple, figures, exemples et references compris. Les soumissions devront parvenir au comite d'organisation avant le 23 fevrier 2001, sous forme electronique, a mailto:recital2001 at univ-tours.fr. En cas d'impossibilite d'envoi par courrier electronique, une soumission "papier" pourra etre admise. Dans ce cas, trois exemplaires devront etre envoyes a l'adresse suivante: Recital 2001 LI (Laboratoire d'Informatique de l'Universite de Tours) E3i, 64, avenue Jean Portalis 37200 Tours France ********** FORMAT DES SOUMISSIONS ********** Les auteurs devront envoyer leur soumission par courrier electronique sous la forme d'un document attache (fichiers ps ou pdf au format A4 et non Lettre US). Le message contiendra le titre de la soumission et les noms des auteurs. Les formats a utiliser pour la redaction sont disponibles sur le site de la conference: http://www.li.univ-tours.fr/taln-recital-2001. ********** CRITERES DE SELECTION ********** Les auteurs sont invites a soumettre des travaux de recherche originaux, n'ayant pas fait l'objet de publications anterieures. Les soumissions seront examinees par au moins deux specialistes du domaine. Seront considerees en particulier : l'importance et l'originalite de la contribution, la correction du contenu scientifique et technique, la discussion critique des resultats, en particulier par rapport aux autres travaux du domaine, la situation des travaux dans le contexte de la recherche internationale, l'organisation et la clarte de la presentation, l'adequation aux themes de la conference. Les articles selectionnes seront publies dans les actes de la conference. ********** POSTERS ********** Une ou deux seances specifiques seront prevues pour des posters (85 x 120 cm). Les propositions de poster suivent les memes regles que les soumissions de communication mais ne devront pas depasser 4 pages. ********** PRESENTATIONS ORALES ********** Les presentations orales dureront 15 minutes et seront suivies de 5 minutes de questions. Il sera possible d'utiliser un retro-projecteur ou un video-projecteur. ********** ACTES ********** Les actes des conferences seront distribues a tous les participants. **************************************************************** English version Submission deadline extended to 3/6/2001 **************************************************************** ********** Recital 2001 : LAST CALL FOR PAPERS ************ ----> SUBMISSION DEADLINE extended : Thursday, 3/06/2001 <---- Recital 2001 will be held in Tours, 2 - 5 July 2001, organized by the LI (Computer Laboratory of Tours University) and LTI (Language and Information Technologies). The official conference languages are French and English. The young researcher conference Recital 2001 will be held jointly with the conference TALN 2001. TALN 2001 is organized in collaboration with ATALA (Association pour le Traitement Automatique des LAngues). ********** TOPICS ********** Papers are invited in all areas of NLP, including (but not limited to): Analysis and comprehension of texts Text generation in natural languages Automatic translation Production of summaries Human Computer Interaction Recital 2001 also invites contributions in the following fields too: Linguistic resources (lexics, electronic dictionaries, corpora, etc.) Lexical Semantics (categorisation, etc.) Time and space Semantics (representation and reasoning) Logic (argumentation, modelisation of intention, etc.) NLP Dedicated architectures (multi-agents systems, neuromimetic networks) Acquisition and automatic learning of resources or knowledge (from corpora, or human/machine interaction) Relations between NLP and talk recognition ********** CALENDAR ********** ----> SUBMISSION DEADLINE: FRIDAY, 2/23/2001 <---- Notification to authors: 4/27/2001 Final version due (camera-ready): 5/11/2001 Conference : 7/2-5/2001 ********** SUBMISSION PROCEDURE ********** The maximum length for papers is 10 pages, in Times 12, single spaced, including figures, examples and references. Electronic submissions must reach the organizing committee before 2/23/2001, sent to mailto:recital2001 at univ-tours. If electronic submission is not possible, 3 hard copies of the paper must reach the organizing committee before 2/23/2001, at the following address: TALN 2001 LI (Laboratoire d'Informatique de l'Universite de Tours) E3i, 64, avenue Jean Portalis 37200 Tours France ********** FORMAT FOR SUBMISSIONS ********** Authors should send their submission as a file attached to an e-mail(ps or pdf files, A4 format and not US Letter format), containing the following information: submission title and author's names. The formats that MUST be used are available on the Conference website: http://www.li.univ-tours.fr/taln-recital-2001. ********** SELECTION CRITERIA ********** Authors are invited to submit original, previously unpublished work. Submissions will be reviewed by at least 2 specialists of the domain. Decisions will be based on the following criteria : Importance and originality of the paper Accuracy of the scientific and technical content Comparison of the results obtained with other relevant work Layout and clarity of the paper Relevance to the topics of the conference Accepted papers will be published in the proceedings of the conference. ********** POSTERS ********** One or two specific sessions for the posters (85 x 120 cm) will be scheduled in the conference. The poster submissions accord to the same rules of paper submission, BUT they should not exceed 4 pages. ********** TALKS ********** Papers should be of 15 minutes duration. 5 minutes will be left for questions. It will be possible to use a overhead projector or a video-projector. ********** COMITE DE PROGRAMME ********** ********** PROGRAM COMMITTEE ********** Pascal Amsili, TALaNa Pierre Beust, GREYC Philippe Blache, LPL Beatrice Bouchou, LI (president) Jean Caelen, CLIPS Cecile Fabre, ERSS Cedric Fairon, NYU, Department of Linguistics Bertrand Gaiffe, LORIA Damien Genthial, CLIPS Gabriel Illouz, LIMSI Denis Maurel, LI Philippe Muller, IRIT Anne Nicolle, GREYC Martin Rajman, EPFL Laurent Romary, LORIA Jose Rouillard, CLIPS Azim Roussanaly, LORIA Jacques Siroux, IRISA LLI/CORDIAL Jacques Vergne, GREYC Jean Veronis, LPL Michael Zock, LIMSI ********** COMITE D'ORGANISATION ********** ********** ORGANIZING COMMITTEE ********** Claire Agafonov, LTI Beatrice Bouchou, LI (president) Alain Cambourian, LTI Alain Delplanque, LTI Nathalie Friburger, LI (president) Nathalie Garric, LTI Paul Gaudin, LTI Manuel Gonzales de Avila, Ciremia Thierry Grass, LTI Denis Maurel, LI Nathalie Rossi, LTI Mohamed Slimane, LI Nicole Vincent, LI ___________________________________________________________________ Message diffus� par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Tue Feb 20 15:46:28 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Tue, 20 Feb 2001 16:46:28 +0100 Subject: Appel: Fifth Workshop on Interlinguas Message-ID: Fifth Workshop on Interlinguas : Call for Papers The call for papers for the Fifth Workshop on Interlinguas is available at http://crl.nmsu.edu/Events/FWOI/FifthWorskhop/ The goal of this workshop is to bring together specialists to work out a practical, cross-language system of semantic relations for use in representing events and states of affairs including, but not limited to, participant relations (e.g., agent, patient, recipient, benefactee, instrument, etc.), spatial relations (e.g., anterior, posterior, superior, inferior, interior, etc.) and temporal relations (e.g., prior-to, following, concurrent, etc.). Papers are invited on: identifying systems of semantic relations and the linguistic devices for expressing them, methods for developing (or extending) such systems of relations, inferencing techniques for exploiting such systems of relations for particular MT tasks, such as disambiguation, reference resolution, the recovery of ellipted information, interpeting noun-noun compounds, metonymy and metaphor, etc. The workshop will be held on Wednesday, September 19, 2001, in conjunction with MT Summit VIII in Santiago de Compostela, Spain. Submission deadline: April 15, 2001 For further information, contact: Steve Helmreich or David Farwell shelmrei at crl.nmsu.edu david at crl.nmsu.edu 505.646.2141 505.646.5108 ___________________________________________________________________ Message diffus� par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Tue Feb 20 15:46:47 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Tue, 20 Feb 2001 16:46:47 +0100 Subject: Soft: 2 annonces Message-ID: /1 Bigram Statistics Package (v0.3) /2 LANGUAGE INDEPENDENT PART-OF-SPEECH TAGGER -------------------------------------------------------------------------- /1 Bigram Statistics Package (v0.3) A newly improved version of the Bigram Statistics Package (v0.3) is now available! This is an easy to use suite of Perl tools for counting and analyzing bigrams in text. It includes a number of the standard tests of association, and also allows users to easily implement others without knowing very much about Perl at all. And it allows users to perform pairwise comparisons of the lists of bigrams found by these tests. This is free software. Get it (or more information) at: http://www.d.umn.edu/~tpederse/code.html Coming Soon - Unicode support! -- # Ted Pedersen http://www.d.umn.edu/~tpederse # # Department of Computer Science tpederse at d.umn.edu # # University of Minnesota Duluth # # Duluth, MN 55812 (218) 726-8770 # -------------------------------------------------------------------------- /2 LANGUAGE INDEPENDENT PART-OF-SPEECH TAGGER Dear Readers , Those interested in the two pieces of NLP software presented below are welcome to contact me directly ( gojol at sunu.rnc.ro ) . Thank you , Dr.ing. Vlad Gojol ---------------------------------- Senior Research Engineer Institutul National de Informatica Bucuresti , Romania ............................................................................ LANGUAGE INDEPENDENT PART-OF-SPEECH TAGGER I created a part-of-speech tagger with an unusual capacity of dealing with large contexts , especially for German . I used Negra ( seemingly the best known German corpus , with free obtainable licence ) . The tagger currently reputed as being the most accurate for German is perhaps TnT . It reports upon this corpus an error rate of 3.4% . But I have found a syste- matic error in Negra : all the occurences of the auxilliary verbs are tagged as auxilliary ( VAFIN ) , though in 50% of the cases they function as finite verbs ( VVFIN ) . I corrected a part of the corpus ( cca 40,000 tokens ) . In this more correct environment ( where the performance of TnT should be probably around 4.5% ) , my tagger gets 1.7% . On another German corpus ( I call it X ) , with comparable contents ( news- paper articles ) and tagset , but with attached EXTERIOR lexicon ( i.e. not extracted from the corpus ) , the result is 2.4% . I also used Susanne ( the only English corpus I could get free ) . The re- ported result for TnT is 3.8% . Mine is 2.8% . On the "A" texts , best paral- lelable with those in Negra , as journalistic , it's 2.3% . By restricting the tagset to a more normal size ( cca 100 tags , determined as optimal af- ter lots of test runs ) , it's 1.3% . Initially I had used a Romanian corpus , with a result of 0.9% ( compared to 1.7% , 2.5% and 4.2% respectively got by the Xerow , Birmingham and Brill taggers ) . The speed is comparable to that of TnT and modifiable by parameter setting , in reverse proportion to the accuracy ( but without affecting it much ) . The incremental operating mode and the data structures segmentation allow running on very small memory computers . There is the advantage of an intuitive output ( no hostile binary matrix ) , in a form analogue to the input of some expert systems . Alternative taggings are output , with scores : unlike with other taggers , they don't refer to individual words , but to whole sentence parts ( repre- senting somehow phrase surfaces of minimum energy ) . Special facilities exist , such as virtual tags , or context essentialisa- tion ( permitting to get the minimal contexts set characteristic to a certain linguisic style , useful not only for maximum accuracy and speed ) etc. Recently added features : wide-character support , the possibility of being called as a simple library routine , or suspending the notion of a file ( a complex files system is emulated into the memory ) . For example ( for the second feature above ) , you can create an instance of the tagger ( let's say for English with the tagset Lancaster ) , call it to tag a cer- tain text buffer ( by writing the resulting tags into another buffer ) and finally kill the instance , all this without using any disc file : t = GojolTagger_new("lancaster"); error_code = GojolTagger_tag(t,input_buffer,output_buffer); GojolTagger_free(t); All is built on two essentially new concepts : organicity and context pro- pagation . I didn't publish anything about them , to keep up their commercial appeal . The accuracy comparable to that of manual tagging made me find many errors in the used corpora : 98 in Negra , 36 in Susanne ; Prof. G. Sampson replied gratefully , saying that it's the first time somebody reports more than 2 errors , and that my findings make necessary a new version of Susanne . The handling of very large contexts could even modify the current tagsets de- sign , by cancelling some unnatural decisions ( motivated only by the incapa- city of the existing taggers to see beyond a 3-tokens neighborhood ) , such as those concerning the auxilliary verbs , participles etc. - so removing some burden from the subsequent stages of text processing . It is written in C ( Linux ) . Demos for German ( Negra ) and English ( Susanne ) are available . .............................................................................. LANGUAGE INDEPENDENT STATISTIC PARSER After learning from a 46,000 words pos-tagged corpus and a 32,000 words parsed ( treebank ) corpus , a 2,000 words text ( not included in any of the two corpora ) is parsed ( tagging excluded ) in 6 seconds ( on a 200 MHz machine ) with 2% incomplete trees ( but for these declared failures , are also provided well formed trees sufficient for a subse- quent translator ) - the extracted grammar having cca 12,000 rules . The Negra corpus of German was used . After learning from a 17,000 words parsed corpus and from the same 46,000 words pos-tagged one , a 2,000 words text included into the first ( but excluded from the second ) , to warrant that the grammar is complete relative to it ( i.e. contains all the rules necessary for its correct parsing ) , is processed in 2 seconds with no incomplete tree - the extracted grammar having cca 7,000 rules . The system is language independent - for English , upon the Susanne corpus , comparable results are obtained . To have an acceptable parser for any other i- diom , you need essentially simply a corpus with 30,000 tag- ged words , from which only 20,000 parsed as well - and for optimal results , 50,000 and 30,000 respectively . The parser may accept a set of rules intended to modify the statistical grammar deduced from the corpus . Moreover , it can take as input only a context-free grammar ( in which case it ceases to be a statistical parser ) , but in this operating mode it requires much time and memory ( during the learning , not during the parsing as such ) if the grammar is over-dimensioned . The statistical grammar is refined not by simply adding the proposed rules , but by modifying the corpus , to exploit all the real contexts possible for them . Semantic processing could be easily inserted at rule re- duction points . Actually this generalized parser can also work as a compiler generator : by appending specific semantic routines , you get efficient compilers for C , Pascal etc. This versatile system has more than 40 parameters which tune the accuracy and speed according to the target language sam- ple . The output is in treebank format and optionally in gra- phic ( with the trees effectively drawn ) one . Linux demos exist for German and English . As only the mi- nimal definition of C is used , it is easily adaptable to any machine ( for other Unix-like operating systems , probably a simple recompilation would be sufficient ) . ___________________________________________________________________ Message diffus� par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Tue Feb 20 15:47:05 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Tue, 20 Feb 2001 16:47:05 +0100 Subject: Appel: ACL-2001 Workshop on Open-Domain Question Answering Message-ID: WORKSHOP ON OPEN-DOMAIN QUESTION ANSWERING ACL'2001 Conference Toulouse, France July 7, 2001 Open-domain question answering (QA) represents a new challenge to both commercial applications and academic research. When users have specific questions, such as "What countries did Clinton visit in 1999?" or "How much does a ThinkPad cost?", they would like to see one (or a few) succint answer(s). This workshop will focus on technical issues that directly apply to this challenge, in particular, theoretical and pragmatic issues involved in the creation, evaluation and implementation of QA techniques. We concentrate on QA that is automatic and either domain independent or working within a large open domain, such as news or technical support. To accommodate this need for automatically finding answers to open-domain questions, several different fields of research come together - information retrieval, natural-language processing and knowledge representation. This workshop will provide a forum for discussions of QA as the combination and integration of techniques from these three fields. We invite papers that deal with QA topics or components in one or more of these fields, such as answer identification using passage retrieval techniques, linguisitc analysis of questions to determine their focus, parse-based matching of questions and answers, text generation as used for formulating answers, deriving answers from knowledge bases, defining confidence measures for answers, etc. Other QA issues of interest are evaluation methods, user interface issues and user studies, integration of QA within larger systems, and commercial applications of QA. Topics of interest include, but are not limited to: - parsing of natural language used in analyzing questions and answers - semantic analysis and categorization of questions and answers - lexical resources and knowledge bases as used in QA - knowledge acquisition and information extraction used in QA - empirical methods for QA - methods for answer selection, synthesis and generation - definitions of answer correctness and answer justification - commercial applications for QA - integration of QA in dialog systems and search systems All papers should specifically focus on question answering. ORGANIZERS: Yael Ravin, T .J. Watson Research Center, IBM, USA John Prager, T .J. Watson Research Center, IBM, USA Sanda Harabagiu, Southern Methodits University, USA PROGRAM COMMITTEE: Jamie Callan, CMU Jaime Carbonell, CMU Donna Harman, NIST Graeme Hirst, Toronto Jerry Hobbs, SRI Christian Jacquemin, LIMSI Liz Liddy, Syracuse Marc Light, MITRE Dekang Lin, Alberta Steve Maiorano, AAT Dan Moldovan, SMU Dragomir Radev, Michigan Tomek Strzalkowski, SUNY Albany Ellen Voorhees, NIST SCHEDULE: Workshop paper submissions April 8, 2001 Notification of acceptance April 30, 2001 Deadline for camera-ready papers May 13, 2001 Workshop date July 7, 2001 SUBMISSION FORMAT AND INSTRUCTIONS: Submissions must be in English, no more than 8 pages long, and in the two-column format prescribed by ACL'2001. Please see http://acl2001.dfki.de/style/ for the detailed guidelines. Submissions should be sent electronically in either Word, pdf, or postscript format (only) no later than April 8, 2001 to: Yael Ravin ravin at us.ibm.com ___________________________________________________________________ Message diffus� par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Tue Feb 20 15:47:23 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Tue, 20 Feb 2001 16:47:23 +0100 Subject: Appel: 2nd SIGdial Workshop on Discourse and Dialogue Message-ID: (We apologize if you receive this message more than once) 1st Announcement 2nd ACL SIGdial Workshop on Discourse and Dialogue Aalborg, Denmark, September 1-2 (Just before Eurospeech 2001-Scandinavia) More up to date information on submission schedule, formats, registration and program committee may be found at the workshop website Description Following up on the successful 1st Workshop in Hong Kong in October 2000, this will be the next in a series of workshops spanning the ACL SIGdial interest area of discourse and dialogue. While there has been a lot of activity in this area, and fairly frequent "specialty" workshops on various sub-topics, until this series there has not been a regular place for such research to be presented in a forum to receive attention from the larger SIGdial community and researchers outside this community. Invited Speakers: to be announced. Topics of Interest We welcome formal, corpus-based, implementational and analytical work on discourse and dialogue, with a focus on the following three themes: (i) Dialogue Systems Spoken, multi-modal, and text/web based dialogue systems including topics such as: * dialogue management models (specific subproblems or general modeling, in particular models for mixed initiative and user-adaptive dialogue); * speech, text, and graphics integration (for understanding or generation); * context-based interpretation and/or response planning,in particular how this contributes to natural interaction; * strategies for handling or preventing miscommuncation (repair and correction types, clarification and underspecificity, grounding and feedback strategies); * utilizing prosodic information for various types of disambiguation; * task-driven versus conversational dialogue; * evaluation of dialogue systems including task complexity measurements. (ii) Corpora and Corpus Tools Corpus-based work on discourse and spoken, text-based and multi-modal dialogue including its support, in particular: * issues and problems in discourse and dialogue annotation; * techniques (including machine learning), tools, coding schemes and data resources for discourse and dialogue studies; * XML-based tools for dialogue access to internet information. (iii) Pragmatic and/or Semantic Modeling The pragmatics and/or semantics of discourse and dialogue (i.e., beyond a single sentence) including the following issues: * the semantics/pragmatics of dialogue acts (including those which are less studied in the semantics/pragmatics framework); * incremental (plan-based,topic-based, etc.) models of discourse/dialogue structure integrating referential and relational structure; * modeling genre-specific aspects of discourse and dialogue structure, including the specific structural aspects of (interactive) digital media; * prosody in discourse and dialogue; * modeling politeness and non-recursive parts of discourse and dialogue; * models of presupposition and accommodation; * operational models of conversational implicature. Submission of Papers and Abstracts The program committee welcomes the submission of papers for full plenary presentation. The papers must be no longer than 10 pages, including title page, examples, references, etc. In addition to this, two additional pages are allowed as an appendix which may include extended example discourses or dialogues, algorithms, graphical representations, etc. Besides papers for full plenary presentation, we encourage the submission of short 4-page papers (inclusive title page, examples, references, etc.) to be combined with a short presentation in the plenary session and a poster presentation. Full papers and short papers should be sent electronically to the e-mail address sigdial2001 at ims.uni-stuttgart.de and must be received no later than May 7. The format to use for papers and abstracts is the same (ACL final paper format). Stylefiles are available at the workshop webpage: http://www.sigdial.org/sigdialworkshop01. Papers must be submitted in pdf (preferred) or postscript format. The title page should include the following information: Title: Authors' names, affiliations, and email addresses: Keywords (up to 5 keywords specifying subject area): Submission type (full paper or short paper submission): Abstract (short summary up to 5 lines): Important Dates Submission of full papers and short papers May 7 Notification June 20 Final submissions August 1 Workshop September 1-2 Workshop Publications Like full papers, short papers will be published in the workshop proceedings. Authors of a selected number of full papers accepted for the workshop proceedings will be asked to send in a version of their paper for the publication in a book on current directions and developments in discourse and dialogue, to be published by a renowned, international publisher. Panel Sessions In addition to the regular paper and abstract submissions, the program committee welcomes proposals for other relevant activities, such as reports of working groups and initiatives, and targeted discussion sessions. The program committee itself intends to organize two panel sessions, the descriptions of which will be given in later announcements, namely one specifically on spoken dialogue systems and the other on the pragmatics/semantics of discourse and dialogue being directly relevant to the first subject. Program Committee Co-Chairs: Jan van Kuppevelt (University of Stuttgart) and Ronnie Smith (East Carolina University) Organizing Committee Laila Dybkjaer (local chair), David Traum, Julia Hirschberg, Ronnie Smith, Jan van Kuppevelt. Contact Information: Questions about submission: Ronnie Smith/Jan van Kuppevelt Questions about local issues: Laila Dybkjaer Miscellaneous: David Traum ___________________________________________________________________ Message diffus� par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Tue Feb 20 15:47:36 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Tue, 20 Feb 2001 16:47:36 +0100 Subject: Conf: TALN 2001 : extension de la date de soumission Message-ID: ********************************************************************** * * TALN 2001 * Traitement Automatique du Langage Naturel * * Universite de Tours * du lundi 2 au jeudi 5 juillet 2001 * * http://www.li.univ-tours.fr/taln-recital-2001/ * mailto::taln2001 at univ-tours.fr * ********************************************************************** (see English version below) ********** TALN 2001 : DERNIER APPEL A COMMUNICATION ********** ----> DATE LIMITE DE SOUMISSION (EXTENSION) : MARDI 6 MARS 2001 <---- TALN 2001 aura lieu a Tours du lundi 2 au jeudi 5 juillet 2001, organise par le LI (Laboratoire d'Informatique de l'Université de Tours) et l'axe LTI (Langues et Technologies de l'information). La conference TALN 2001 comprendra des communications scientifiques, des conferenciers invites, des seances de demonstration et posters, ainsi que des tutoriels. Les langues officielles de la conference sont le francais et l'anglais. TALN 2001 est organisee sous l'egide de l'ATALA (Association pour le Traitement Automatique des LAngues) et se tiendra conjointement a la conference pour jeunes chercheurs RECITAL 2001 (appel a communications a paraitre separement). ********** THEMES ********** Les communications pourront porter sur tous les themes habituels du TALN, incluant, de facon non limitative: lexique morphologie syntaxe semantique pragmatique discours analyse generation resume dialogue traduction automatique approches logiques, symboliques et statistiques TALN 2001 souhaite egalement accueillir des travaux de domaines proches dans lesquels le TALN joue un role important, dans la mesure ou l'accent est mis sur la composante TALN : traitement de la parole (prosodie, linguistique, pragmatique) traitement de l'ecrit aspects cognitifs terminologie acquisition de connaissances a partir de textes extraction d'information recherche documentaire linguistique de corpus linguistique mathematique utilisation d'outils de TALN pour la modelisation linguistique enseignement assiste, enseignement des langues. Sont aussi attendus des travaux sur des applications du TALN, implementees et evaluees, faisant ressortir leurs aspects scientifiques et les enseignements tires. Des demonstrations de systemes pourront etre proposees, independamment ou en complement d'articles scientifiques. L'emploi du temps de la conference comprendra une session pour ces demonstrations. ********** CALENDRIER ********** ----> DATE LIMITE DE SOUMISSION (EXTENSION) : MARDI 6 MARS 2001 <---- Notification aux auteurs : vendredi 27 avril 2001 Version finale (pret-a-clicher) : vendredi 11 mai 2001 Conference : du lundi 2 au jeudi 5 juillet 2001 ********** MODALITES DE SOUMISSION ********** Les articles soumis seront rediges en francais (ou en anglais par les non-francophones). Ils ne devront pas depasser 10 pages en Times 12, espacement simple, figures, exemples et references compris. Les soumissions devront parvenir au comite d'organisation avant le 6 mars 2001, sous forme electronique, a mailto:taln2001 at univ-tours.fr. En cas d'impossibilite d'envoi par courrier electronique, une soumission "papier" pourra etre admise. Dans ce cas, trois exemplaires devront etre envoyes a l'adresse suivante: TALN 2001 LI (Laboratoire d'Informatique de l'Universite de Tours) E3i, 64, avenue Jean Portalis 37200 Tours France ********** FORMAT DES SOUMISSIONS ********** Les auteurs devront envoyer leur soumission par courrier electronique sous la forme d'un document attache (fichiers ps ou pdf au format A4 et non Lettre US). Le message contiendra le titre de la soumission et les noms des auteurs. Les formats a utiliser pour la redaction sont disponibles sur le site de la conference: http://www.li.univ-tours.fr/taln-recital-2001. ********** CRITERES DE SELECTION ********** Les auteurs sont invites a soumettre des travaux de recherche originaux, n'ayant pas fait l'objet de publications anterieures. Les soumissions seront examinees par au moins deux specialistes du domaine. Seront considerees en particulier : L'importance et l'originalite de la contribution, La correction du contenu scientifique et technique, La discussion critique des resultats, en particulier par rapport aux autres travaux du domaine, La situation des travaux dans le contexte de la recherche internationale, L'organisation et la clarte de la presentation, L'adequation aux themes de la conference. Les articles selectionnes seront publies dans les actes de la conference. ********** DEMONSTRATIONS ET POSTERS ********** Une ou deux seances specifiques seront prevues pour des demonstrations (presentations logicielles) et des posters (85 x 120 cm). Les propositions de demonstration ou de poster suivent les memes regles que les soumissions de communication mais ne devront pas depasser 4 pages. ********** PRESENTATIONS ORALES ********** Les presentations orales dureront 20 minutes et seront suivies de 10 minutes de questions. Il sera possible d'utiliser un retro-projecteur ou un video-projecteur. ********** ACTES ********** Les actes de la conference seront distribues a tous les participants. Le Comite de redaction de la revue Traitement Automatique des Langues (t.a.l.) sélectionnera deux articles pour publication. ********************************************************************** * * ENGLISH VERSION * ********************************************************************** ********** TALN 2001 : FINAL CALL FOR PAPERS ********** ----> EXTENDED SUBMISSION DEADLINE: TUESDAY, 3/6/2001 <---- TALN 2001 will be held at Tours on July, 2 - 5 2001, organized by the LI (Computer Laboratory of Tours University) and LTI (Language and Information Technologies). The conference includes paper presentations, invited speakers, tutorials and software demonstrations. The official conference languages are French and English. TALN 2001 is organized in collaboration with ATALA (Association pour le Traitement Automatique des LAngues) and will be held jointly with the young researcher conference RECITAL 2001 (a separate call for papers will follow). ********** TOPICS ********** Papers are invited in all areas of NLP, including (but not limited to): lexicon morphology syntax semantics pragmatics discourse parsing generation abstraction/summarisation dialogue translation logical, symbolical and statistical approaches TALN 2001 also invites contributions in fields for which NLP plays an important role, as long as these contributions emphasize their NLP dimension : speech processing text processing cognition terminology knowledge acquisition information retrieval documentary research corpus-based linguistics mathematical linguistics management and acquisition of linguistic resources computer assisted learning NLP tools for linguistic modelization TALN 2001 also welcomes submissions focusing on NLP applications that have been implemented, tested and evaluated and emphasizing the scientific aspects and conclusions drawn. Software demonstrations can be proposed, either independently or in connection with a paper proposal. Specific sessions for the demos will be scheduled in the conference. ********** CALENDAR ********** ----> EXTENDED SUBMISSION DEADLINE: TUESDAY, 3/6/2001 <---- Notification to authors: 4/27/2001 Final version due (camera-ready): 5/11/2001 Conference : 7/2-5/2001 ********** SUBMISSION PROCEDURE ********** The maximum length for papers is 10 pages, in Times 12, single spaced, including figures, examples and references. Electronic submissions must reach the organizing committee before 3/6/2001, sent to mailto:taln2001 at univ-tours.fr. If electronic submission is not possible, 3 hard-copies of the paper must reach the organizing committee before 3/6/2001, at the following address: TALN 2001 LI (Laboratoire d'Informatique de l'Universite de Tours) E3i, 64, avenue Jean Portalis 37200 Tours France ********** FORMAT FOR SUBMISSIONS ********** Authors should send their submission as a file attached to an e-mail(ps or pdf files, A4 format and not US Letter format), containing the following informations: submission title and author's names. The formats that MUST be used are available on the Conference web site: http://www.li.univ-tours.fr/taln-recital-2001/ . ********** SELECTION CRITERIA ********** Authors are invited to submit original, previously unpublished work. Submissions will be reviewed by at least 2 specialists of the domain. Decisions will be based on the following criteria : Importance and originality of the paper Accuracy of the scientific and technical content Comparison of the results obtained with other relevant work Layout and clarity of the paper Relevance to the topics of the conference Accepted papers will be published in the proceedings of the conference. ********** DEMOS AND POSTERS ********** One or two specific sessions for the demos and the posters (85 x 120 cm) will be scheduled in the conference. The demo or poster submissions accord to the same rules of paper submission, BUT they should not exceed 4 pages. ********** TALKS ********** Papers should be of 20 minutes duration. 10 minutes will be left for questions. It will be possible to use a overhead projector or a video-projector. ********** PROCEEDINGS ********** The conference proceedings will be given to all participants. The editorial staff of the journal Traitement Automatique des Langues (t.a.l.) will select two papers for publication. ********** COMITE DE PROGRAMME ********** ********** PROGRAMME COMMITTEE ********** (le comite de programme sera entoure d'un large comite de lecture) (the program committee will be supervised by a broad reviewing committee) Pascal Amsili, TALaNa Frederic Bechet, LIA Philippe Blache, LPL Christian Boitet, CLIPS-GETA Pierrette Bouillon, ISSCO Beatrice Daille, IRIN Laurence Danlos, LORIA/TALaNa Claire Gardent, LORIA Eric Laporte, CERIL Denis Maurel, LI (president) Piet Mertens, CCL Jean-Marie Pierrel, LORIA Martin Rajman, EPFL Owen Rambow, ATT Labs-Research Jacques Siroux, IRISA LLI/CORDIAL Jean Veronis, LPL Pierre Zweigenbaum, DIAM ********** COMITE D'ORGANISATION ********** ********** ORGANIZING COMMITTEE ********** Claire Agafonov, LTI Beatrice Bouchou, LI Alain Cambourian, LTI Alain Delplanque, LTI Nathalie Friburger, LI Nathalie Garric, LTI Paul Gaudin, LTI Manuel Gonzales de Avila, Ciremia Thierry Grass, LTI Denis Maurel, LI (president) Nathalie Rossi, LTI Mohamed Slimane, LI Nicole Vincent, LI ___________________________________________________________________ Message diffusé par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Tue Feb 20 15:48:07 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Tue, 20 Feb 2001 16:48:07 +0100 Subject: Appel: BUlletin de Linguistique Appliquée et Générale Message-ID: CALL FOR PAPERS The theme for the next number of BULAG (BUlletin de Linguistique Appliquée et Générale) Theme: Internet and Natural Language Processing Coordonated by: Henri MADEC Papers to be sent to: Henri MADEC Centre de Recherche en Linguistique Lucien Tesnière Faculté des Lettres 30, rue Mégevand 25030 Besançon cedex France henri.madec at univ-fcomte.fr Submission deadline: 04/30/2000 Information concerning the papers format : Papers should be in the region of 10 pages. Each paper should have the following form. Chaque article devra être édité sous la forme suivante : Title Author Name of research Centre University City Country Résumé en français Key-words Abstract in English Key-words Paper References You can download a word 95/97 format model from the following address: http://tesniere.univ-fcomte.fr/ressourc/blgmoden.doc You can download an RTF format model from the following adress: http://tesniere.univ-fcomte.fr/ressourc/blgmoden.rtf Document format: Upper margin Lower margin Left margin Right margin Headers Footers Height x Width Font sizes: principal title 14, other title 10, text 10 Interparagraph spacing Space between paragraph title and paragraph 2,5 cm. 2,5 cm. 2 cm. 2 cm. 1,25 cm. 1,25 cm. 21 cm. x 14,8 cm. 6 pts. 3 pts. File formats Word 95, Word 97, RTF, Fonts Times New Roman (if you use other fonts please supply these with your paper) Submission: by E-Mail (attached file) to: henri.madec at univ-fcomte.fr or by post, in a 1.44 MB diskette, PC format, to Henri MADEC Centre de Recherche en Linguistique Lucien Tesnière Faculté des Lettres 30, rue Mégevand 25030 Besançon cedex France ___________________________________________________________________ Message diffusé par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Tue Feb 20 15:48:17 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Tue, 20 Feb 2001 16:48:17 +0100 Subject: Appel: NAACL2001 3 workshops Message-ID: NAACL 2001 Workshop on 1/ WordNet and Other Lexical Resources: 2/ Workshop on Automatic Summarization 2001 3/ Adaptation in Dialogue Systems ------------------------------------------------------------------- 1/ WordNet and Other Lexical Resources: Applications, Extensions and Customizations http://www.seas.smu.edu/~moldovan/mwnw/ NAACL 2001 Workshop Carnegie Mellon University, Pittsburgh 3 and 4 June, 2001 Sponsored by the Association for Computational Linguistics Special Interest Group on the Lexicon. Previously announced as two different workshops: - WordNet: Extensions and NLP Applications - Customizing Lexical Resources Lexical resources have become important basic tools within NLP and related fields. The range of resources available to the researcher is diverse and vast - from simple word lists to complex MRDs and thesauruses. The resources contain a whole range of different types of explicit linguistic information presented in different formats and at various levels of granularity. Also, much information is left implicit in the description, e.g. the definition of lexical entries generally contains genus, encyclopaedic and usage information. The majority of resources used by NLP researchers were not intended for computational uses. For instance, MRDs are a by-product of the dictionary publishing industry, and WordNet was an experiment in modelling the mental lexicon. In particular, WordNet has become a valuable resource in the human language technology and artificial intelligence. Due to its vast coverage of English words, WordNet provides with general lexico-semantic information on which open-domain text processing is based. Furthermore, the development of WordNets in several other languages extends this capability to trans-lingual applications, enabling text mining across languages. For example, in Europe, WordNet has been used as the starting point for the development of a multilingual database for several European languages (the EuroWordNet project). Other resources such as the Longman Dictionary of Contemporary English and Roget's Thesaurus have also been used for various NLP tasks. The topic of this workshop is the exploitation of existing resources for particular computational tasks such as Word Sense Disambiguation, Generation, Information Retrieval, Information Extraction, Question Answering and Summarization. We invite paper submissions that include but are not limited to the following topics: - Resource usage in NLP and AI - Resource extension in order to reflect the lexical coverage within a particular domain; - Resource augmentation by e.g. adding extra word senses, enriching the information associated with the existing entries. For instance, recently, several extensions of the WordNet lexical database have been initiated, in the United States and abroad, with the goal of providing the NLP community with additional knowledge that models pragmatic information not always present in the texts but required by document processing; - Improvement of the consistency or quality of resources by e.g. homogenizing lexical descriptions, making implicit lexical knowledge explicit and clustering word senses; - Merging resources, i.e. combining the information in more than one resource e.g. by producing a mapping between their senses. For instance, WordNet has been incorporated in several other linguistic and general knowledge bases (e.g. FrameNet and CYC); - Corpus-based acquisition of knowledge; - Mining common sense knowledge from resources; - Multilingual WordNets and applications; Paper submission Submissions must use the NAACL latex style or Microsoft Word style (see workshop website). Paper submissions should consist of a full paper (6 pages or less). Submission procedure Electronic submission only. For U.S. papers please send the pdf or postscript file of your paper to: moldovan at seas.smu.edu. Please submit papers from other countries to w.peters at dcs.shef.ac.uk. Because review is blind, no author information is included as part of the paper. A separate identification page must be sent by email including title, all authors, theme area, keywords, word count, and an abstract of no more than 5 lines. Late submissions will not be accepted. Notification of receipt will be e-mailed to the first author shortly after receipt. Please address any questions to moldovan at seas.smu.edu or w.peters at dcs.shef.ac.uk Important dates Paper submission deadline: February 20, 2001 Notification of acceptance: March 10, 2001 Camera ready due: March 25, 2001 Workshop date: June 3 and 4, 2001 Organizers Sanda Harabagiu, SMU, sanda at seas.smu.edu Dan Moldovan, SMU, moldovan at seas.smu.edu Wim Peters, University of Sheffield, wim at dcs.shef.ac.uk Mark Stevenson, University of Sheffield, marks at dcs.shef.ac.uk Yorick Wilks, University of Sheffield, yorick at dcs.shef.ac.uk Programme Committee Roberto Basili (Universita di Roma Tor Vergata) Martin Chodorow (Hunter College of CUNY) Christiane Fellbaum (Princeton University) Ken Haase (MIT) Sanda Harabagiu (SMU) Graeme Hirst (University of Toronto) Robert Krovetz, NEC Claudia Leacock (ETS) Steven Maiorano (AAT) Rada Mihalcea (SMU) Dan Moldovan (SMU) Simonetta Montemagni (Istituto di Linguistica Computazionale, Pisa) Martha Palmer (University of Pennsylvania) Maria Tereza Pazienza (Universita di Roma Tor Vergata) Wim Peters (University of Sheffield) German Rigau (Universitat Politecnica de Catalunya) Mark Stevenson (University of Sheffield) Randee Tengi (Princeton University) Paola Velardi (University of Roma "La Sapienza") Ellen Voorhees (NIST) Piek Vossen (Sail Labs) Yorick Wilks (University of Sheffield) --------------------------------------------------------------------- 2/ Workshop on Automatic Summarization 2001 (pre-conference workshop in conjunction with NAACL2001) Sunday, June 3, 2001 Pittsburgh, Pennsylvania, USA sponsored by ACL (Association for Computational Linguistics) MITRE Corporation New submission deadline: Febuary 23, 2001 Organizing Committee: Jade Goldstein Carnegie Mellon University jade+ at cs.cmu.edu Chin-Yew Lin USC/Information Sciences Institute cyl at isi.edu Program Committee: Breck Baldwin Baldwin Language Tech Hsin-Hsi Chen National Taiwan University Udo Hahn Universitaet Freiburg Eduard Hovy USC/Information Sciences Institute Hongyan Jing Columbia University Elizabeth Liddy Syracuse University Daniel Marcu USC/Information Sciences Institute Inderjeet Mani MITRE Shigeru Masuyama Toyohashi University of Technology Marie-Francine Moens Katholieke Universiteit Leuven Vibhu Mittal Google Research Sung Hyon Myaeng Chungnam National University Akitoshi Okumura NEC Chris Paice Lancaster University Dragomir Radev University of Michigan, Ann Arbor Karen Sparck-Jones University of Cambridge Tomek Strzalkowski State University of New York, Albany Simone Teufel Columbia University Workshop Website: http://www.isi.edu/~cyl/was-naacl2001 (for the latest update) I. OVERVIEW II. CALL FOR PAPERS III. FORMAT FOR SUBMISSION I. OVERVIEW The problem of automatic summarization poses a variety of tough challenges in both NL understanding and generation. A spate of recent papers and tutorials on this subject at conferences such as ACL, ANLP/NAACL, ACL/EACL, AAAI, ECAI, IJCAI, and SIGIR point to a growing interest in research in this field. Several commercial summarization products have also appeared. There have been several workshops in the past on this subject: Dagstuhl in 94, ACL/EACL in 97, the AAAI Spring Symposium in 98, and ANLP/NAACL in 2000. All of these were extremely successful, and the field is now enjoying a period of revival and is advancing at a much quicker pace than before. NAACL'2001 is an ideal occasion to host another workshop on this problem. II. CALL FOR PAPERS The Workshop on Automatic Summarization program committee invites papers addressing (but not limited to): Summarization Methods: use of linguistic representations, statistical models, NL generation for summarization, production of abstracts and extracts, multi-document summarization, narrative techniques in summarization, multilingual summarization, text compaction, multimodal summarization (including summarization of audio), use of information extraction, studies and modeling of human summarizers, improving summary coherence, concept fusion, use of thesauri and ontologies, trainable summarizers, applications of machine learning, knowledge-rich methods. Summarization Resources: development of corpora for training and evaluating summarizers, annotation standards, shared summarization tools, document segmentation, topic detection, and clustering related to summarization. Evaluation Methods: intrinsic and extrinsic measures, on-line and off-line evaluations, standards for evaluation, task-based evaluation scenarios, user studies, inter-judge agreement. Workshop Themes: 1. Summarization Applications 2. Multidocument Summarization 3. Multilingual Text Summarization 4. Evaluation and Text/Training Corpora 5. Generation for Summarization 6. Topic Identification for Summarization 7. Integration with Web and IR Access III. FORMAT FOR SUBMISSION Submissions must use the ACL latex style or Microsoft Word style WAS-submission.doc (both available from the Automatic Summarization workshop web page). Paper submissions should consist of a full paper (5000 words or less, including references). SUBMISSION QUESTIONS Please send submission questions to cyl at isi.edu SUBMISSION PROCEDURE Electronic submission only: send the pdf (preferred), postscript, or MS Word form of your submission to: cyl at isi.edu. The Subject line should be "NAACL2001 WORKSHOP PAPER SUBMISSION". Because reviewing is blind, no author information is included as part of the paper. An identification page must be sent in a separate email with the subject line: "NAACL2001 WORKSHOP ID PAGE" and must include title, all authors, theme area, keywords, word count, and an abstract of no more than 5 lines. Late submissions will not be accepted. Notification of receipt will be e-mailed to the first author shortly after receipt. DEADLINES Paper submission deadline: Feburary 23, 2001 Notification of acceptance for papers: March 23, 2001 Camera ready papers due: April 6, 2001 Workshop date: June 3, 2001 --------------------------------------------------------------------- 3/ NAACL 2001 Workshop on Adaptation in Dialogue Systems Webpage: www.cs.utah.edu/~cindi/AdaptDial.html Overview The purpose of this workshop is to bring together researchers investigating the application of learning and adaptation to dialogue systems, both speech and text based. Methods for learning and adaptation show promise for enhancing the robustness, flexibility, and overall accuracy of dialogue systems. While researchers in many parts of computational linguistics who use these methods have begun to form communities, the burgeoning set of activities within dialogue has remained relatively disparate. We are interested in adaptation that includes learning procedures as well as decision making methods aimed at dynamically reconfiguring dialogue behavior based on the context. We would also like to explore techniques that allow a dialogue system to learn with experience or from data sets gathered from empirical studies. Researchers looking at methods to automatically improve different modules of dialogue systems, or the system as a whole, have not had many opportunities to come together to share their work. We thus welcome submissions from researchers supplementing the traditional development of dialogue systems with techniques from machine learning, statistical NLP, and decision theory. Call For Papers We solicit papers from a number of research areas, including: - Use of machine learning techniques at all levels of dialogue, from speech recognition to generation; from dialogue strategy to user modeling - Adapting to the user as a dialogue progresses - Dialogue as decision making under uncertainty - User and user group modeling - Use of corpora in developing components of dialogue systems, including issues in annotation - Evaluation of adaptive dialogue systems - Comparison of different techniques in applying adaptive techniques to dialogue We also hope to include a session for the demonstration of working systems, as time permits. The demonstration sessions will be open to anyone who wishes to bring their adaptive conversational systems for demonstration to other members of the workshop. Presenters are asked to submit a paper that is specifically directed at a demonstration of their current systems. Important Dates (2001): Paper submission deadline: Feb 19 Notification of acceptance for papers: Mar 16 Camera ready papers due: Mar 30 Workshop date: Jun 4 Paper Submission Electronic submission only: send the postscript or pdf form of your submission to: timpaek at microsoft.com. The Subject line should be "NAACL2001 WORKSHOP PAPER SUBMISSION". A cover page should be included with title, all authors, theme area, keywords, word count, and an abstract of no more than 5 lines. Late submissions will not be accepted. Notification of receipt will be e-mailed to the first author shortly after receipt. Please address any questions to timpaek at microsoft.com Submissions must use the NAACL latex style or Microsoft Word style. Paper submissions should consist of a full paper (6 pages or less). The templates are available at the workshop web site. Organizers Eric Horvitz Microsoft Research horvitz at microsoft.com Tim Paek Microsoft Research timpaek at microsoft.com Cindi Thompson University of Utah cindi at cs.utah.edu Program Committee Jennifer Chu-Carroll IBM Peter Heeman Oregon Graduate Institute Diane Litman AT & T Labs Candace Sidner MERL Marilyn Walker AT & T Labs ___________________________________________________________________ Message diffus� par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Tue Feb 20 15:51:02 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Tue, 20 Feb 2001 16:51:02 +0100 Subject: Appel: SEMPRO-2001 Message-ID: COGNITIVELY PLAUSIBLE MODELS OF SEMANTIC PROCESSING SEMPRO-2001 (A workshop in conjunction with the Annual Meeting of the Cognitive Science Society) July 31st, Edinburgh University http://www.hcrc.ed.ac.uk/~sempro/ The goal of this workshop is to provide a forum to present models of semantic processing (computational and non-computational) motivated by psychological evidence or corpus studies. Topics of interest include: - incrementality and underspecification in semantic processing - lexical access and disambiguation - semantic composition (e.g., interpretation of modifiers such as adjectives, of modal expressions, of negation) - anaphora resolution - scope assignment - detection and exploitation of discourse structure - semantic interpretation in dialogues (e.g., models of grounding) We would especially like to encourage the exchange of results between psychological experimentation, computational modelling, and corpus-based work. PROGRAM COMMITTEE (tentative): Massimo Poesio, Alan Garnham, Maria Lapata, Julie Sedivy, Rosemary Stevenson, Peter Wiemer-Hastings SUBMISSION PROCEDURE: Anonymous extended abstracts of at most 5 pages should be submitted by e-mail to sempro at cogsci.ed.ac.uk. Include the words 'Submission for SEMPRO 2001' in the Subject line. Accepted formats: ASCII, postscript, pdf. DATES: Papers due: April 15th Acceptance Notification: June 15th. ___________________________________________________________________ Message diffus� par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Tue Feb 20 15:53:26 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Tue, 20 Feb 2001 16:53:26 +0100 Subject: Appel: CoNLL-2001 Message-ID: APOLOGIES FROM MULTIPLE SUBMISSIONS CALL FOR PAPERS CoNLL-2001 Fifth Computational Natural Language Learning Workshop Toulouse, France, July 6-7, 2001 http://lcg-www.uia.ac.be/conll2001/ BACKGROUND CoNLL is the yearly workshop organized by SIGNLL, the Association for Computational Linguistics Special Interest Group on Natural Language Learning (http://www.aclweb.org/signll/). Previous CoNLL meetings were held in Madrid (1997), Sydney (1998), Bergen (1999) and Lisbon (2000). The 2001 event will be held as a two-days workshop at the 39th Annual Meeting of the Association for Computational Linguistics (ACL), July 6-11, 2001 in Toulouse, France. This year, a special theme will be the focus of the workshop: Interaction and Automation in Language Learning Resources Apart from this special theme, the workshop will accept contributions about language learning topics, including, but not limited to: - Computational models of human language acquisition - Computational models of the origins and evolution of language - Machine learning methods applied to natural language processing tasks (speech processing, phonology, morphology, syntax, semantics, discourse processing, language engineering applications) - Symbolic learning methods (Rule Induction and Decision Tree Learning, Lazy Learning, Inductive Logic Programming, Analytical Learning, Transformation-based Error-driven Learning) - Biologically-inspired methods (Neural Networks, Evolutionary Computing) - Statistical methods (Bayesian Learning, HMM, maximum entropy, SNoW, Support Vector Machines) - Reinforcement Learning - Active learning, ensemble methods, meta-learning - Computational Learning Theory analyses of language learning - Empirical and theoretical comparisons of language learning methods - Models of induction and analogy in Linguistics This year's workshop will also accept submissions for a shared task (segmenting a text into clauses-clausing). THE WORKSHOP Main Session Theme: Interaction and Automation in Language Learning Resources The purpose of the special theme is to present and discuss state-of-the-art learning mechanisms for the automated acquisition of language resources (dictionaries, ontologies, grammars) or the automated adaptation of natural language resources/processors to new domains or languages. The dimensions of learning that are of interest for this session include: - The integration of humans/linguists in the learning process - The structure of the training data - The kind of knowledge that is learned - General study of learning methods that are suitable for natural language related tasks Lately there have been new learning mechanisms that use either large amounts of raw data or small sets of carefully constructed tagged training samples. Learning language can be construed as learning numbers or parameters for some statistical or symbolic system, or learning rules assigning structures to input data (or a mix of those). Learning can be done off-line, which introduces the problem of interpreting (if needed) the derived knowledge before its use in an NLP engine; or on-line, which raises user interaction problems. Different approaches are tailored to solve different kinds of problems subject to a different balance of requirements (large vs. small training set, tagged vs. untagged training data, results needs interpretation or can be used as is, etc.). While this session aims at presenting the largest panorama of learning techniques, we encourage submission of work on semi-automated learning techniques that involve interaction with a human during the learning process or the intervention of a linguist for interpreting results. Special Session: Shared Task - Segmenting Text Into Clauses We invite groups to take part in a shared task: Segmenting a Text Into Clauses (Clausing). Participating groups will be provided with the same training and testing material, and will all use the same evaluation criteria, thus allowing comparison between various learning technologies. After Chunking, the CoNLL-2000 shared task, Clausing can be seen as the next step towards a full parsing. More information on this shared task is available at: http://lcg-www.uia.ac.be/conll2001/clauses/ Invited Session: Learning Computational Grammars There will be a special session devoted to the presentation and discussion of results of the EU Learning Computational Grammars project (Coordinator: John Nerbonne). Project participants include: the University of Groningen (The Netherlands, coordinator), University of Antwerp (Belgium), the University of Tuebingen (Germany), SRI Cambridge (UK), the University College Dublin (Ireland), the University of Geneva (Switzerland), and Xerox Grenoble (France). Invited Speaker (to be announced) SUBMISSIONS Format for Paper Submissions for Main Session Submit an abstract of maximum 1500 words (Postscript or ASCII) by April 6, 2001 electronically to the address below. Authors of accepted abstracts will be invited to produce a full paper to be published in the proceedings of the workshop, which will be available at the workshop for participants, and distributed afterwards by the ACL. Submit main session abstracts to: Walter Daelemans, walter.daelemans at uia.ua.ac.be Centrum Nederlandse Taal en Spraak. Linguistics, Department of Germanic languages and literature UIA, University of Antwerp Universiteitsplein 1, B-2610 Wilrijk, Belgium or Rémi Zajac, zajac at crl.nmsu.edu Computing Research Laboratory New Mexico State University PO Box 30001 Dept. 3CRL Las Cruces NM 88003 USA Format For Shared Task Submissions Submit an abstract of maximum 1500 words describing the learning approach, and your results on the test set by April 6, 2001 to the address below (preferably by email). A special section of the proceedings will be devoted to a comparison and analysis of the results and to a description of the approaches used. Submit shared task submissions to: Erik Tjong Kim Sang, erikt at uia.ua.ac.be Centrum Nederlandse Taal en Spraak Linguistics, Department of Germanic languages and literature UIA, University of Antwerp Universiteitsplein 1, B-2610 Wilrijk, Belgium Important dates Deadline for Abstract Submission: April 6, 2001 Deadline for Shared Task Submission: April 6, 2001 Notification: April 27, 2001 Deadline camera-ready full paper: May 16, 2001 Workshop: July 6/7, 2001 PROGRAMME COMMITTEE Walter Daelemans (co-chair) Rémi Zajac (co-chair) Thorsten Brants (Xerox PARC, USA) Michael Brent (Washington University in Saint Louis, USA) Claire Cardie (Cornell University, USA) James Cussens (University of York, UK) Herve Dejean (University of Tuebingen, Germany) Gregory Grefenstette (Xerox Grenoble, France) Raymond Mooney (University of Texas at Austin, USA) John Nerbonne (Groningen University, Netherlands) Kemal Oflazer (Sabanci University, Turkey) Miles Osborne (University of Edinburgh, UK), David Powers (Flinders University, Australia) Ronan Reilly (University College Dublin, Ireland) Dan Roth (University of Illinois at Urbana-Champaign, USA) Erik Tjong Kim Sang (University of Antwerp, Belgium) Antal van den Bosch (Tilburg University, Netherlands) Yorick Wilks (University of Sheffield, UK) -- ___________________________________________________________________ Message diffusé par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Thu Feb 22 17:27:40 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Thu, 22 Feb 2001 18:27:40 +0100 Subject: ATALA: Journee sur la structuration de terminologie Message-ID: (English version below) ATALA : Journée d'étude du samedi 10 mars 2001 Structuration de terminologie : objectifs, méthodes et évaluation Organisée par Thierry Hamon et Adeline Nazarenko 9h30 Thierry Hamon (LIPN, Université Paris-Nord) Adeline Nazarenko (LIPN, Université Paris-Nord) Introduction 10h00 Didier Bourigault (ERSS, Université Toulouse le Mirail) Cécile Fabre (ERSS, Université Toulouse le Mirail) Extraction de syntagmes et analyse distributionnelle 10h45-11h Pause 11h00 Nathalie Aussenac-Gilles (IRIT, Toulouse) Brigitte Biébow (LIPN, Université Paris-Nord) Sylvie Szulman (LIPN, Université Paris-Nord) Vers un environnement intégré pour la struturation de terminologies : Terminae 11h45 Gaël de Chalendar (LIMSI-CNRS) Brigitte Grau (LIMSI-CNRS) Extraction de terminologies structurées à partir de corpus généraux 12h00-14h30 Déjeuner 14h30 Anne Condamines (ERSS, Université Toulouse le Mirail) La notion de marqueurs de relation conceptuelle et ses possibilités de prise en compte par le TAL 15h15 Patrick Séguéla (IRIT, Toulouse) Extraction de relations lexicales pour la structuration de terminologie 16h-16h15 Pause 16h15 Farid Cerbah (Dassault Aviation, Saint-Cloud) La structuration de terminologies vue au travers de deux applications 17h Fin de la journée d'étude CHU Pitié - 91 bd de l'Hôpital - 75013 Paris Amphi D RdC du bâtiment principal, à gauche des ascenseurs Entrée libre Adhésion à l'association ATALA recommandée Site ATALA : http://www.atala.org Page Web de cette journée : http://www.atala.org/je/je-010310.html ======================================================================= ATALA Workshop. Saturday 10 March 2001 Terminology structuring: purpose, methods and evaluation organised by Thierry Hamon (LIPN, Université Paris-Nord) and Adeline Nazarenko (LIPN, Université Paris-Nord) Will take place at CHU Pitié - 91 bd de l'Hôpital - 75013 Paris Amphitheatre D ---------------------------------------------------------------- Entrance free Applications for membership of ATALA is welcomed http://www.atala.org ----------------------------------------------------------------- 9h30 Thierry Hamon (LIPN, Université Paris-Nord) Adeline Nazarenko (LIPN, Université Paris-Nord) Introduction 10h00 Didier Bourigault (ERSS, Université Toulouse le Mirail) Cécile Fabre (ERSS, Université Toulouse le Mirail) Phrase extraction and distributional analysis 10h45-11h Break 11h00 Nathalie Aussenac-Gilles (IRIT, Toulouse) Brigitte Biébow (LIPN, Université Paris-Nord) Sylvie Szulman (LIPN, Université Paris-Nord) Toward an integrated environment for terminology structuring: Terminae 11h45 Gaël de Chalendar (LIMSI-CNRS) Brigitte Grau (LIMSI-CNRS) Extraction of structured terminologies from general language corpora 12h30-14h30 Lunch 14h30 Anne Condamines (ERSS, Université Toulouse le Mirail) Conceptual relationship patterns and their use in NLP 15h15 Patrick Séguéla (IRIT, Toulouse) Extraction of lexical relations for terminology structuring 16h-16h15 Break 16h15 Farid Cerbah (Dassault Aviation, Saint-Cloud) Terminology structuring in two applicationsx 17h00 End of Workshop ___________________________________________________________________ Message diffusé par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Thu Feb 22 17:28:06 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Thu, 22 Feb 2001 18:28:06 +0100 Subject: Appel: ACL 2001 2 workshops Message-ID: 1/ ACL/EACL Workshop on Sharing Tools and Resources for Research and Education 2/ Call for papers Workshop on Data-driven MT ACL'2001 Conference ------------------------------------------------------------------- 1/ CALL FOR CONTRIBUTIONS ACL/EACL Workshop on Sharing Tools and Resources for Research and Education Co-organised by ELSNET Toulouse, Saturday 7th July 2001 BACKGROUND: At a workshop at ACL 2000 in Hong Kong dedicated to Infrastructures for Global Collaboration there was an agreement between the main professional organisations in NLP and Speech (ACL and ISCA), and ELSNET, and the other meeting participants, that it would be useful to aim at a broadly supported, joint repository or catalogue for tools and materials for the language and speech communities. An ELSNET-sponsored workshop on educational issues held at EACL99 concluded that certain non-transient infrastructures needed to be instigated to raise the public perception of educational issues in NLP. It also concluded that a repository of shared materials, appropriately indexed for educational usage, would be a useful point of departure. This workshop will build on the consensus reached at these previous workshops. There will be two clear foci: one upon instruments for sharing tools and resources in general that addresses practical problems, and the other upon the technological and infrastructural issues surrounding the educational uses of repositories. Good examples of existing initiatives in this area are among others the ACL Natural Language Software Registry (hosted at DFKI, http://registry.dfki.de) which was set up as a repository for tools for the distinct fields of Human Language Techology (HLT), the ELRA/ELDA, LDC, TELRI and Elsnet resources catalogues and repositories (http://www.icp.inpg.fr/ELRA/, http://www.ldc.upenn.edu/, http://www.telri.de and http://www.elsnet.org/resources.html), OLAC (a worldwide network of language archives at www.language-archives.org), and JEWELS (http://www.elsnet.org/jewels), an as-yet incomplete EU funded website for educational materials in Language and Speech. A third theme concerns how to build upon existing initiatives as sources of data or inspiration. AIM AND SCOPE OF THE WORKSHOP: The main goal of the workshop is to discuss methods for the improvement and extension of existing repositories; the educational uses of repositories; the closer interlinking between different kinds of repositories (tools and resources); global infrastructures for the achievement of joint actions. However, we expect the scope of the workshop to be much wider than that, as the issues addressed are of general interest to everybody who believes that sharing tools and resources is essential for the progress of research and education in our field. Contributions of papers and demonstrations are solicited that address the above themes. The following list of topics is suggestive rather than exhaustive: * Repositories versus catalogues * Mechanisms and infrastructures for sharing and describing content * Repository management * Standards for exchange, description, and annotation * Metadata descriptions * Quality assessment * Structure and content of an NLP/CL repository * Tools and materials for NLP/CL education * Web-based teaching methods for NLP/CL SUBMISSION REQUIREMENTS FOR PAPERS * Electronic submissions only (PostScript, Word, or PDF), following the appropriate ACL latex style or Microsoft Word style. Submissions should not exceed eight (8) pages, including references. You can download the appropriate style or template files using the following link: http://acl2001.dfki.de/style/. In case of problems with the submission format, please contact one of the co-chairs. * Submissions to either co-chair (mros at cs.um.edu.mt and declerck at dfki.de). All submissions will be acknowledged. * Please provide a list of keywords in the separate header page and indicate the best fitting subtopic(s) from the above list. SUBMISSION REQUIREMENTS FOR DEMONSTRATIONS * Demos may be submitted with or without an accompanying paper. * Please write a 2-page description of the demo and send to either co-chair. Please let us know about special hardware requirements over and above the standard PC + beamer without internet access provided by default CONFIRMED COMMITTEE MEMBERS - Thierry Declerck (DFKI) Co-chair (Repository) declerck at dfki.de - Mike Rosner (Malta) Co-chair (Education) mros at cs.um.edu.mt - Steven Bird (U. Penn) - Bill Black (UMIST) (UMIST, Manchester, UK) wjb at co.umist.ac.uk - Gosse Bouma gosse at let.rug.nl (University of Groningen) - Koenraad de Smedt desmedt at uib.no (University of Bergen) - Claire Gardent (CNRS, Nancy) claire.gardent at loria.fr - Steven Krauwer (Utrecht University) steven.krauwer at elsnet.org - Donna Harman (NIST) - Julia Hirschberg (ATT, ISCA) - Jun'ichi Tsujii (Tokyo) - Andy Way (Dublin City University) away at compapp.dcu.ie DEADLINES * Submission Deadline: 6th April 2001 * Notification Date: 27th April 2001 * Camera ready copy due: 16th May 2001 PROVISIONAL WEBSITE http://www.cs.um.edu.mt/~mros/toulouse FOR FURTHER INFORMATION CONTACT Michael Rosner email: mros at cs.um.edu.mt Thierry Duclerc email: declerck at dfki.de ------------------------------------------------------------------- 2/ Call for papers Workshop on Data-driven MT ACL'2001 Conference Toulouse, France Invited speaker: Hermann Ney, RWTH Aachen Deadline for paper submissions: April 6, 2001 Deadline for notification of paper acceptance: April 27, 2001 Deadline for camera-ready papers: May 16, 2001 Workshop Date: July 7, 2001 Details on submissions listed below. With the increased availability of online corpora, data-driven approaches have become central to the NL community. A variety of data-driven approaches have been used to help build Machine Translation systems -- example-based, statistical MT, and other machine learning approaches - and there are all sorts of possibilities for hybrid systems. We wish to bring together proponents of as many techniques as possible to engage in a discussion of which combinations will yield maximal success in translation. We propose to center the workshop on Data Driven MT, by which we mean all approaches which develop algorithms and programs to exploit data in the development of MT, primarily the use of large bilingual corpora created by human translators, and serving as a source of training data for MT systems. We are specifically interested in papers about * statistical machine translation (modeling, training, search) * machine-learning in translation * example-based machine translation * acquisition of multilingual training data * evaluation of data driven methods (also with rule-based methods) * combination of various translation systems; integration of classical rule-based and data driven approaches * word/sentence alignment methods An especially important question that we wish to address is which techniques are best for each of the subparts of a complete MT system - e.g. learning grammars, building lexicons, parsing input data, determining transfer principles, generating target text, etc. We will strongly encourage papers on systems which show demonstrable progress over previously chosen methods, and which have been integrated in an actual end-to-end system. Test results or demos will be given strongest preference for participation. Organizers: Jessie Pinkham, Microsoft Research jessiep at microsoft.com Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Fri Feb 23 12:00:47 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Fri, 23 Feb 2001 13:00:47 +0100 Subject: Appel: MT Summit VIII: workshop Message-ID: ( Apologies if you have already seen an announcement for this workshop ) MT Evaluation: Who Did What To Whom A workshop held in conjunction with Machine Translation Summit VIII Saturday, September 22nd, 2001, Santiago de Compostela, Spain CALL FOR PAPERS Introduction Many measures and methods of evaluating MT systems have been developed over the years. The ISLE project, funded jointly by the European Union and the National Science Foundation of the USA, is continuing with work started in the EU's EAGLES project on systematizing these measures and procedures. This workshop will be the fourth in a series that report on and flesh out portions of the systematization. The main thrust of the work is to build up schemes that classify various aspects of import for MT, including user needs, the suggested system characteristics and associated metrics for measuring each of these. The classification schemes relate to ISO work on software evaluation. The work is intended to be useful to those who are considering using machine translation, those interested in comparative evaluation of several MT systems and to MT system developers. A fuller account of the ISLE evaluation work and an overview of the current classification schemes can be found at http://www.isi.edu/natural-language/mteval/. By the time of the MT Summit, the ISLE project will have organized or been involved in a number of workshops on MT evaluation, namely at LREC in Athens, AMTA in Mexico, Geneva Workshop, and NAACL in Pittsburgh. Participants are encouraged, but not required, to get involved with the Geneva Workshop or NAACL Workshop as these are hands-on exercises in MT. The results of the previous workshops, as possible, will be presented here and feedback based on them serves directly the goal of developing proposals of concrete usefulness to the whole community. This workshop will be seen as a preliminary attempt at reaching conclusions which synthesize results. Information about the previous workshops can be found at: LREC: http://www.icp.grenet.fr/ELRA/lrec2000.html AMTA: http://www.isi.edu/natural-language/conferences/AMTA2000.html NAACL 2001: http://www.cs.cmu.edu/~ref/naacl2001.html MT Evaluation workshop: An invitation to get your hands dirty! http://www.issco.unige.ch/projects/isle/mt-eval-workshop.html, and finally at the MT Summit VIII: http://www.eamt.org/summitVIII. Papers We invite submission of papers along the themes discussed above. The questions and issues to be answered are diverse. All papers on evaluation and evaluation issues will be considered, but preference will be given to papers relating to the ISLE framework. The following questions suggest possible evaluation threads within the framework. * What kind of metrics are useful for what system characteristics? * What system characteristics reflect what user needs? * Is there a radical difference between evaluation focusing on research or development needs and evaluation focusing on end-user needs? * When should real-world data be used, and what is the impact of using it? * What constitutes a valid metric? How can you demonstrate that a metric is valid? * What are the advantages/disadvantages of specific metrics? * What kinds of tools automate the evaluation process? Can the process (or any part of it) be automated? What are the difficulties inherent in choosing particular metrics for automation? * What kinds of tasks are suited to which evaluation schemes? * How can we use the evaluation process to speed or improve the MT development process? * How can we evaluate MT when MT is a small part of the data flow? How independent is MT of the subsequent processing? Cleaning up the data improves performance, but does it improve it enough? How do we quantify that? Submission Guidelines Papers may be submitted electronically to Sandra Manzi, (Sandra.Manzi at issco.unige.ch) by the submission date. The format may be RTF, Microsoft Word, or PostScript. Any specialized fonts should be included in the submission package. Users are advised to follow the main conference formatting as described at: http://www.eamt.org/summitVIII/guidelines.html. Submission for review: papers of no more than 6000 words are expected. Submission for publication: A template will be provided for accepted papers. Important Dates Paper submission deadline April 15, 2001 Notification of acceptance May 31, 2001 Final camera-ready due July 1, 2001 Schedule and Venue This one-day workshop will take place on September 22nd, 2001, after the regular conference. The main conference site contains information about registration and accommodation for both the conference and any satellite events, including this workshop. About Santiago Santiago de Compostela in North West Spain (Galicia) was the most visited pilgrimage shrine in the Middle Ages, and to this day the Road to Santiago is a popular route for walkers through France and northern Spain. The goal is the imposing 11th century cathedral containing the relics of St. James the Great. But the well-preserved historical center of the city offers much more: medieval streets, excellent restaurants, ancient churches, monasteries, palaces, etc. The venue for the conference is the Hostal de los Reyes Católicos, founded in 1499 as a Royal hospital for pilgrims; a magnificent building in the Spanish Renaissance style, and now a hotel (the oldest and one of the most beautiful in the world). Those staying at the Hostal will have a once-in-a-lifetime experience, but there is also accommodation nearby in many other good hotels, all within easy walking distance of the center and the Hostal. Santiago de Compostela has its own airport with daily direct flights from Barcelona, Madrid, Brussels and London. Contact Points and Organizing Committee: For any further information, please contact Sandra Manzi, (sandra.manzi at issco.unige.ch) TIM/ISSCO -- University of Geneva 40 blvd du Pont d'Arve CH-1211 GENEVA 4 (Switzerland) Tel: +41-22-705.8680 Fax: +41-22-705.8689 Organizing Committee E. Hovy, ISI, hovy at isi.edu B. Maegaard, CST, bente at cst.ku.dk S. Manzi, ISSCO, sandra.manzi at issco.unige.ch M. King, ISSCO, margaret.king at issco.unige.ch F. Reeder, MITRE, freeder at mitre.org ___________________________________________________________________ Message diffusé par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Fri Feb 23 12:12:40 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Fri, 23 Feb 2001 13:12:40 +0100 Subject: Jobs: 5 offres Message-ID: 1/ Computational Linguist, Syntax Classification 2/ Computational Linguist, Text Processing Classification 3/ Linguistic Testing Engineer Classification 4/ Phonetic Lexicographer Classification 5/ Speech Engineer, Prosody Classification Conversay 15375 NE 90th Street Redmond WA 98052 http://www.conversa.com/ ------------------------------------------------------------------------------ 1/ CONVERSAY - Job Description Title Computational Linguist, Syntax Classification Date Updated 14, Dec. 2000 Department Language Development\Core Reports To (Title) Director, Core Engineering Job Description The successful candidate will develop and extend current automatic syntactic analyzers and taggers and be willing to work on text normalization components as well. In addition, s\he should have a predisposition to work with naturally-occurring text corpora and a strongly empirical orientation to syntactic issues. Knowledge, Skills and Abilities * PhD in Linguistics or degree in Computer Science and at least a M.A. in Linguistics * Computational Syntax, NLP, Statistics * Experience with automatic learning and syntactic tagging systems * Knowledge of existing NLP tools * C/C++ * Previous experience with speech processing and applications a plus * Near native knowledge of at least one of the following languages is a strong plus: Portuguese, Dutch, Swedish, Finnish, German, Korean, Japanese, Mandarin or Cantonese Chinese Principal Duties and Responsibilities ? Maintain proprietary Taggers and Parsers. ? Create new NLP tools as required for several diverse languages. ? Help create and maintain text normalization component. Supervision * Able to work with limited supervision. * Position does not involve supervision duties. Decision Making * Adaptable and Creative * Self-motivated Interaction * Able to communicate effectively with scientists and developers. * Willing to work closely with staff syntactician and other linguists and programmers. Equipment * No equipment specifications Physical Requirements * Sustain movements of the fingers, wrists, hands or arms (keyboard work). * Must have the ability to receive detailed information through oral and written communication, to express or exchange information by means of oral and written. Additional Information * Must be willing to relocate to the Seattle/Bellevue/Redmond (WA) area. ------------------------------------------------------------------------------ 2/ CONVERSAY - Job Description Title Computational Linguist, Text Processing Classification Date Updated Department Core Engineering - Language Development Reports To (Title) Manager of Core Technology, Language Development group Job Description The successful candidate will assist in the creation, maintenance and extension of a text/language processing component for multiple languages used by Conversay's proprietary text-to-speech and automatic speech recognition engine. Knowledge, Skills and Abilities (including education) * Thorough understanding of phonology and morphology. * Basic C programming skills and/or experience with scripting languages such as Perl. * Advanced degree in linguistics or computer science (Ph.D. a strong plus). * Knowledge of other areas of linguistics and natural language processing a strong plus. * Familiarity with text normalization/tokenization issues a strong plus. * Knowledge of multiple languages a strong plus (especially Portuguese, Dutch, Swedish, Finnish, German, Korean, Japanese, Mandarin or Cantonese Chinese). * Previous experience with speech applications a plus. Principal Duties and Responsibilities * Extend current text/language processing component to adapt it to different languages, focusing on the following areas: character processing, written word and sentence boundary detection, text normalization, tokenization, text-to-pronunciation, phonology, morphology, lexical access. * Create, extend and maintain new text/language processing modules in the same areas listed above. * Perform any other duties which may be assigned or necessary. Supervision * Position does not involve supervision duties. Decision Making * Must be able to work with limited supervision. * Must be independent, self-motivated and responsible. Interaction * Must be able to interact with linguists, programmers and speech scientists. Equipment * Position does not require knowledge of any specific equipment. Physical Requirements * Sustain movements of the fingers, wrists, hands or arms (keyboard work). * Must have the ability to receive detailed information through oral and written communication, to express or exchange information by means of oral and written. Additional Information * Must be willing to relocate to the Seattle/Bellevue/Redmond (WA) area. ------------------------------------------------------------------------------ 3/ CONVERSAY - Job Description Title Linguistic Testing Engineer Classification Date Updated Department Core Engineering - Language Development Reports To (Title) Mike Aibinder (Director, Core Engineering) Job Description The successful candidate will design, implement, and run suites of automated linguistic tests for Conversay's proprietary text-to-speech and speech recognition system for multiple languages. Knowledge, Skills and Abilities (including education) * Previous industry experience in speech technology / language processing, OR advanced degree in linguistics or a closely related field. * Experience in using scripting or programming languages, especially C, C++, Perl, Visual Basic or Visual Test. * Experience with design & use of automated test tools a plus. * Previous experience with speech applications a strong plus. * Native or near-native knowledge of one of the following languages a strong plus: Portuguese, Dutch, Swedish, Finnish, German, Korean, Japanese, Mandarin or Cantonese Chinese. Principal Duties and Responsibilities * Design and implement automated tools and scripts to evaluate the accuracy and functionality of core language components of Conversay software. For example, write tools, scripts, and expected-behavior frames for testing the text-normalization component. * Work with the Quality Assurance team to design regression tests for core language components. Evaluate bugs reported by QA and direct those bugs to the appropriate members of the Core Engineering team. * Work with the Usability and Quality Assurance team to evaluate user interactions with the language engines, e.g. intelligibility of speech synthesis. * Perform any other duties which may be assigned or necessary. Supervision * Position does not involve supervision duties. Decision Making * Must be able to work with limited supervision. * Must be independent, self-motivated and responsible. Interaction * Must be able to interact with linguists, programmers and speech scientists. * See Principal Duties and Responsibilities above for work with QA and Usability teams. Equipment * Position does not require knowledge of any specific equipment. Physical Requirements * Sustain movements of the fingers, wrists, hands or arms (keyboard work). * Must have the ability to receive detailed information through oral and written communication, to express or exchange information by means of oral and written. Additional Information * Must be willing to relocate to the Seattle/Bellevue/Redmond (WA) area. ------------------------------------------------------------------------------ 4/ CONVERSAY - Job Description Title Phonetic Lexicographer Classification Date Updated Department Core Engineering - Language Development Reports To (Title) Director of Core Engineering Job Description The successful candidate will be responsible for phonetic transcription work in several languages. Duties include: research and analysis to determine specifications for phonetic processing modules, research and purchase of lexical resources, creation and maintenance of lexicons, and analysis of speech and text corpora. The ongoing results of this work will be used in the development of Conversay's proprietary speech recognition and synthesis engines. Knowledge, Skills and Abilities (including education) * Ph.D. in Linguistics with focus on empirical phonetic study * Experience with data and corpus analysis * Native (or near-native) speaker of Japanese or Korean a strong plus * Familiarity with Perl or other scripting/programming languages a strong plus * Familiarity with use of relational databases a strong plus Principal Duties and Responsibilities * Determine phone sets and transcription standards for lexicons in several languages * Determine lexical entries for various application-specific lexicons * Maintain and update existing lexicons * Identify issues and requirements for evaluating phonetic output * Other areas of speech/text collection, analysis, and evaluation as needed Supervision * Position does not involve supervision duties Decision Making * Must be able to work with limited supervision * Must be independent, self-motivated, and responsible Interaction * Must be able to interact with linguists, programmers, speech scientists, and native speakers Equipment * No special knowledge required Physical Requirements * Sustain movements of the fingers, wrists, hands or arms (keyboard work) * Must have the ability to receive detailed information through oral and written communication, to express or exchange information by means of oral and written Additional Information * Must be willing to relocate to the Seattle/Bellevue/Redmond (WA) area ------------------------------------------------------------------------------ 5/ CONVERSAY - Job Description Title Speech Engineer, Prosody Classification Date Updated Department Core Engineering - Language Development Reports To (Title) Director, Core Engineering Job Description The successful candidate will assist in the creation and extension of prosodic components for multiple languages used by Conversay's proprietary text-to-speech and automatic speech recognition engine. Knowledge, Skills and Abilities (including education) * Thorough understanding of prosody and phonology. * C programming. * Advanced degree in linguistics or computer science (Ph.D. a strong plus). * Knowledge of other areas of linguistics and natural language processing a strong plus. * Knowledge of multiple languages a strong plus (especially Portuguese, Dutch, Swedish, Finnish, German, Korean, Japanese, Mandarin or Cantonese Chinese). * Previous experience with speech applications a plus. Principal Duties and Responsibilities * Extend existing prosody module of engine in order to adapt it to different languages. * Create, extend and maintain new prosody module(s). * Perform any other duties which may be assigned or necessary. Supervision * Position does not involve supervision duties. Decision Making * Must be able to work with limited supervision. * Must be independent, self-motivated and responsible. Interaction * Must be able to interact with linguists, programmers and speech scientists. Equipment * Position does not require knowledge of any specific equipment. Physical Requirements * Sustain movements of the fingers, wrists, hands or arms (keyboard work). * Must have the ability to receive detailed information through oral and written communication, to express or exchange information by means of oral and written. Additional Information * Must be willing to relocate to the Seattle/Bellevue/Redmond (WA) area. ___________________________________________________________________ Message diffus� par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From pb at lpl.univ-aix.fr Fri Feb 2 16:51:13 2001 From: pb at lpl.univ-aix.fr (Philippe Blache) Date: Fri, 2 Feb 2001 17:51:13 +0100 Subject: Appel: TSD-2001 Message-ID: From: tsd2001 Matousek _____________________________________________________________________ This message is posted to several lists. We apologize if you receive multiple copies. Please forward it to everyone who might be interested. _____________________________________________________________________ TTTTTTTT SSSS DDDDD 2222 0000 0000 111 TT SSS SSS DD DDD 222 222 000 000 000 000 1111 TT SSS DD DDD 222 000 000 000 000 11111 TT SSSS DD DD 222 000 000 000 000 111 TT SSS DD DDD 222 000 000 000 000 111 TT SSS SSS DD DDD 2222 000 000 000 000 111 TT SSSS DDDDD 22222222 0000 0000 111 _____________________________________________________________________ An International Conference on Text, Speech and Dialogue (TSD 2001) September 10 - 13, 2001 Zelezna Ruda, Czech Republic _____________________________________________________________________ F I R S T A N N O U N C E M E N T A N D C A L L F O R P A P E R S _____________________________________________________________________ TSD 2001 will be organized by the Faculty of Applied Sciences, University of West Bohemia, Plzen (Pilsen), and the Faculty of Informatics, Masaryk University, Brno, under the auspices of the Dean of the Faculty of Applied Sciences of the University of West Bohemia. Conference topics: ------------------ TSD 2001 will be concerned with topics in the field of natural language processing, in particular: - corpora, texts and transcription; - speech analysis, recognition and synthesis; - their intertwinnig within NL dialogue systems. Topics of the TSD 2001 Conference will include (but are not limited to): - text corpora and tagging; - transcription problems in spoken corpora; - sense disambiguation; - links between text and speech oriented systems; - parsing issues, especially parsing problems in spoken texts; - multilingual issues, especially multilingual dialogue systems; - information retrieval and text/topic summarization; - speech modeling; - speech segmentation; - speech recognition; - text-to-speech synthesis; - speech and motions; - dialogue systems; - development of dialogue strategies; - assistive technologies based on speech and dialogue; - applied systems and software. The official language of the event will be English, but papers on issues relating to text and speech processing in languages other than English are strongly encouraged. Format of the conference: ----------------------- TSD 2001 will be an international conference with a limited number of active participants. The conference program will include presentation of three invited papers by keynote speakers, a limited number of general oral presentations, and a poster/demonstration sessions. Papers will be presented in plenary or topic oriented sessions. A special attention will be paid to the arrangement of thematic oriented poster sections extended by short oral presentations. Proceedings: ------------ The contributions to the conference will be published in proceedings that will be made available to participants at the time of the conference. The proceedings will be published by Springer in the series of Lecture Notes of Artificial Intelligence (LNAI). Venue: ------ The international conference will take place in the comfortable hotel Horizont in Sumava Mountains. The hotel is located 1100 m above sea level in the Bohemian Forest Nature Preserve and 3 km far from the centre of Zelezna Ruda town. Social events: -------------- The international conference will also include some social events and trips to the most popular places - Sumava National Park, Black and Devil's lake, Laka lake, district city of Klatovy, Klenova castle and Grosser Arber in Bayerischer Wald on the German side of the border. How to reach Zelezna Ruda: ----------------------------- Zelezna Ruda has very good train connections with Prague, Pilsen and Munich. Distances of the nearest airports (Prague-Ruzyne, Munich) from Zelezna Ruda are about 200 km. More detailed travel information will be posted on the TSD 2001 Web site in due course. Registration Cost: ------------------ Registration fee is $220 (including meals, accommodation, organizing costs, conference proceedings, social events). Student reductions will be available. Accommodation: -------------- The hotel Horizont has 90 double rooms. Each room has its own shower toilet, telephone, nd TV set. The hotel also offers many attractive hotel services. Important dates: ---------------- March 15, 2001 Preliminary registration and deadline for submission of papers April 30, 2001 Notification of acceptance or rejection May 30, 2001 Camera-ready paper submission Sept. 10-13, 2001 TSD 2001 International program committee: -------------------------------- Frederick Jelinek, USA - general chair Hynek Hermansky, USA - executive chair Genevieve Baudoin, France - speech Frantisek Cermak, Czech Rep. - text Attila Ferencz, Romania - speech Eva Hajicova, Czech Rep. - text, speech Patrick Hanks, GB - text Eduard Hovy, USA - text, speech Adam Kilgariff, GB - text Ivan Kopecek, Czech Rep. - speech, text Steven Krauwer, Netherland - text Karel Kucera, Czech Rep. - text Vaclav Matousek, Czech Rep. - speech Rosamund Moon, GB - text Elmar Noeth, Germany - speech Karel Pala, Czech Rep. - text Nikola Pavesic, Slovenia - speech Vladimir Petkevic, Czech Rep. - text Josef Psutka, Czech Rep. - speech E.G. Schukat-Tallamazini, Germany - speech Pavel Skrelin, Russia - speech Taras Vintsiuk, Ukraine - speech Yorick Wilks, GB - text Organizing committee: --------------------- Vaclav Matousek (chair) Helena Benesova Kamil Ekstein Jana Hesova Svatava Kindlova Jana Kleckova Ivan Kopecek Jana Krutisova Josef Masek Pavel Mautner Roman Moucek Jana Ocelikova Karel Pala Pavel Slavik Petr Sojka Karel Tauser Registration: ------------- The registration fee should be paid directly by bank transfer to: Komercni banka Plzen-mesto, Goethova 1, CZ-305 95 Plzen account number : 4811530257/0100 purchase order : 5204/0003/00 special ID code: your birth date in the form YYMMDD (year - month - day), e.g. 550425 account holder: University of West Bohemia, Univerzitni 8, CZ - 306 14 Plzen stating: TSD 2001 and your name Submission of papers: ------------------------ Full papers (max. 8 pages in Springer LNCS format) will be required to reach a decision about acceptance or rejection. First versions of papers submitted for acceptance could be prepared in ASCII format only. Full papers should be submitted to the TSD 2001 Secretariat, preferably by email (tsd2001 at kiv.zcu.cz), by March 15th, 2001. Please contact the Conference Secretariat if receipt of your email submission is not acknowledged within 7 days. It is intended to post abstracts of papers accepted on the TSD 2001 web site in advance of the conference. Please include the following information with your paper: - title of paper, author name(s), author(s) affiliation(s) - e-mail/address/fax of author(s) contact(s) - presentation preference: oral or poster/demonstration. Authors of accepted papers will be requested to send their papers in LateX and PostScript form (in LNCS format) to the conference secretariat by e-mail before June 1st. LaTeX word processor is required. Format instructions (and LNCS LaTeX format) will be available to authors on the TSD 2001 Web site. The conference proceedings will be traditionally published by Springer-Verlag in LNCS/LNAI series (numbers of previous proceedings - LNAI 1692 and LNAI 1902). Conference secretariat: ----------------------- All correspondence regarding the conference should be addressed to: Ms. Helena Benesova University of West Bohemia in Pilsen Faculty of Applied Sciences Department of Computer Science Univerzitni 8 CZ - 306 14 PLZEN Czech Republic Tel: (+420 19) 7491 212, 27 62 50 Fax: (+420 19) 7491 213 E-mail: tsd2001 at kiv.zcu.cz To obtain more information please visit the TSD 2001 Web site: http://www-kiv.zcu.cz/events/tsd2001 ---------------------------- cut here ------------------------------- TSD 2001, September 10-13, 2001, Zelezna Ruda, Czech Republic Preliminary registration Please return this form to the Conference Secretariat Name: Affiliation: Address: Phone: Fax: E-mail: I would like to participate in TSD 2001 as a [ ] Full participiant [ ] Student [ ] I propose to submit a full paper entitled: Preferred presentation: [ ] oral [ ] demo / poster ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From pb at lpl.univ-aix.fr Fri Feb 2 16:51:58 2001 From: pb at lpl.univ-aix.fr (Philippe Blache) Date: Fri, 2 Feb 2001 17:51:58 +0100 Subject: Appel: CIAA-2001 Message-ID: From: Maurel Denis My apologies if you have already seen this, or if you receive more than one copy! ---------- SECOND CALL FOR PAPERS Sixth International Conference on Implementation and Application of Automata CIAA 2001 University of Pretoria July 23-25, 2001 ---------- This conference concerns research on all aspects of implementation and application of automata and related structures. Automata theory is the foundation of computer science. Its applications have spread to almost all areas of computer science and many other disciplines. In addition, there is a growing number of software systems designed to manipulate automata, regular expressions, grammars, and related structures; examples include AGL, AMORE, Automate, FADELA, FinITE, FireLite, FLAP, FSM, Grail, INR, MONA, and Turing's World. The purpose of this conference is to bring together members of the academic, research, and industrial community who have an interest in implementation and application of automata to demonstrate and analyze their work and to explain the problems they have been solving. SCOPE OF THE CONFERENCE We solicit papers and demos on all aspects of implementation and application of automata and related structures, including but not limited to: * Bioinformatics and automata * Complexity of automata operations * Compilers and automata * Computer-aided verification and automata * Concurrency and automata * Data structure design for automata * Data and image compression and automata * Design and architecture of automata software * Digital libraries and automata * Document engineering and automata * Editors, environments and automata * Experimental studies and practical experiences * Industrial applications and automata * Natural language processing and automata * Networking and automata * New algorithms for manipulating automata * Object-Oriented Modeling and automata * Pattern-matching and automata * Speech and speaker recognition and automata * Structured and semi-structured documents and automata * Symbolic manipulation environments for automata * Teaching and automata * Text processing and automata * Techniques for graphical display of automata * VLSI and automata * Viruses, related phenomena and automata * World-wide web and automata SUBMISSION OF PAPERS Authors are requested to submit an electronic version (in PostScript or LaTeX form) or six hard copies of an extended abstract (arriving) by April 2, 2001. An extended abstract should start with the title, each author's name, affiliation, and e-mail address, and a one-paragraph summary of the results and ideas, and be sent to: ciaa2001 at cs.up.ac.za or CIAA 2001 ATTENTION: OPV5-20 Department of Computer Science University of Pretoria Pretoria, South Africa 0002 The extended abstract should provide sufficient detail to allow the Program Committee to evaluate its validity, quality, and relevance to the conference. The extended abstract should be at most ten (10) pages long using 11-point font with ample margins. If appropriate, proof details omitted in the paper may be added in an appendix. Authors will be notified of acceptance or rejection by May 1, 2001. Final copies of accepted papers must be submitted by June 18, 2001. We expect the proceedings to appear in the Springer-Verlag Lecture Notes in Computer Science Series after the conference. (See for example, LNCS 1260 and LNCS 1436 for the proceedings of two previous conferences.) We will distribute a preproceedings for participants at the conference. Extended versions of selected papers from the proceedings of the conference series will be solicited for publication in special issues of Theoretical Computer Science (TCS) and International Journal of Foundations of Computer Science (IJFCS), alternating each year with the CIAA 2001 special issue appearing in TCS. DEMOS We encourage the submission of software demos. Developers wishing to demonstrate their software should submit a two-page description to the address given above by April 2, 2001, outlining the design of their system and their computing needs (if any). INVITED SPEAKERS Gregor v. Bochmann, Ottawa, Canada, CIAA 2001 PROGRAM COMMITTEE B. Boigelot (Liege) J.-M. Champarnaud (Rouen) M. Crochemore (Marne la Vallee) O. Ibarra (UCSB) L. Karttunen (Xerox Europe) N. Klarlund (AT&T) D. Maurel (Tours) M. Mohri (AT&T) J.-E. Pin (Paris) K. Salomaa (Queen's) H. Seidl (Trier) B. Watson (Co-chair) (Pretoria) D. Wood (Co-Chair) (HKUST) S. Yu (Western Ontario) IMPORTANT DATES April 2, 2001 Submission deadline May 1, 2001 Acceptances and rejections sent out June 18, 2001 Submission deadline for preproceedings July 23-25, 2001 Conference dates Sept. 21, 2001 Submission deadline for SV-LNCS SPONSORING ORGANIZATIONS ACM SIGACT, EATCS, University of Pretoria PREVIOUS CONFERENCES CIAA 2000 website WIA'99 website WIA'98 website CIAA 2001 WEB SITES Pretoria Site Hong Kong Site ---------- Prof.Dr. Bruce W. Watson Co-chair of the 2001 Conference on Implementation and Application of Automata bwatson at OpenFIRE.org or bwatson at cs.up.ac.za or watson at win.tue.nl Please DO NOT send me any large emails without asking first. ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From pb at lpl.univ-aix.fr Fri Feb 2 16:53:27 2001 From: pb at lpl.univ-aix.fr (Philippe Blache) Date: Fri, 2 Feb 2001 17:53:27 +0100 Subject: Appel: TAL Special Issue Message-ID: From: Pierrette Bouillon %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% ***************************************************************** Call for papers ***************************************************************** SEMANTIC LEXICONS IN NATURAL LANGUAGE PROCESSING Special issue of the French journal TAL edited by: Pierrette Bouillon (TIM/ISSCO, Gen?ve) and Evelyne Viegas (Microsoft/Natural Language Group, Redmond) Submission deadline: April 1, 2001 http://www.atala.org/tal/appel-semlex.html **************************************************************** SCOPE No one would argue about the importance of semantic lexicons for Natural Language Processing applications such as machine translation, automatic indexing, information extraction, text generation, etc. However, there is no agreement on the type of information to use, how to represent it or how to acquire it automatically. This special issue directly addresses this difficult topic by investigating how lexical semantic theories relate to applications in NLP. We will emphasize the following questions: - Which theory for which application? - How to acquire information automatically? - How to use it in applications? TOPICS (NOT LIMITATIVE) - Acquisition of semantic lexicons - Lexical semantics in NLP applications - Generic versus specific resources? - Which lexical semantic theory for which application? - Types of lexical information - Reuse of existing lexical data FORMAT AND SUBMISSIONS Authors must use the HERMES style files for LateX and Word at . Submissions (30 pages maximum, double spaced, Helvetica 12) must be sent electronically to Pierrette Bouillon () and Evelyne Viegas (). LANGUAGE Articles can be written in French or in English, but English will only be accepted from non-French speaking authors. PROGRAM COMMITTEE - Pierrette Bouillon (TIM/ISSCO, Gen?ve) - Paul Buitelaar (DFKI, Saarbr?cken) - Nicoletta Calzolari (Istituto Di Linguistica Computazionale, Pisa) - Ann Copestake (Cambridge University, Cambridge) - C?cile Fabre (Univ. Toulouse-Le-Mirail, Toulouse) - Christiane Fellbaum (Princeton University, Princeton) - Thierry Fontenelle (Luxembourg) - Mari Olsen (Microsoft, Natural Language Group, Redmond) - Pierre Popowich (Gavagai Technology, Vancouver) - James Pustejovsky (Brandeis University) - Pascale Sebillot (Irisa, Rennes) - Fr?d?rique Segond (Xerox Research Centre Europe, Grenoble) - Evelyne Viegas (Microsoft, Natural Language Group, Redmond) - Piek Vossen (SailLabs, Antwerpen) - R?mi Zajac (New Mexico State University, Computing Research Laboratory) JOURNAL T.A.L. (http://www.atala.org/tal/) The international journal Traitement Automatique des Langues (TAL) has been published since 1969 by the French Association pour le Traitement Automatique des Langues (ATALA) with the support of the Centre National pour la Recherche Scientifique (CNRS). The journal TAL covers all fields of computational linguistics and its aim is to provide mainly (but not only) French speaking researchers and students with publications in all domains of computational linguistics. It appears three times a year and is distributed by HERMES. T.A.L. EDITORIAL BOARD Ann Abeill? (Universit? Paris 7) Pierrette Bouillon (TIM/ISSCO, Gen?ve) Philippe Blache (CNRS, Aix-en-Provence) -- Chief Editor Dani?le Cl?ment (Bergische Universit?t Wuppertal) Christophe d'Alessandro (LIMSI-CNRS, Orsay) -- Chief Editor Anne Condamines (CNRS, Toulouse le Mirail) Claire Gardent (Universit?t des Saarlandes) -- Chief Editor Marc El-B?ze (Universit? d'Avignon) Jean-Louis Lebrave (CNRS, Paris) Piet Mertens (Katholieke Universiteit Leuven) ?velyne Tzoukermann (Bell Labs) Bernard Victorri (ENS, Paris) Pierre Zweigenbaum (AP-HP, Paris 6) %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% --Boundary_(ID_AgsLXsl9GXQ6uyPwRMwh+w)-- ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From pb at lpl.univ-aix.fr Fri Feb 2 16:53:41 2001 From: pb at lpl.univ-aix.fr (Philippe Blache) Date: Fri, 2 Feb 2001 17:53:41 +0100 Subject: Appel: TALN'2001 (Workshops) Message-ID: From: Maurel Denis ********************************************************************** * * TALN 2001 * Traitement Automatique du Langage Naturel * * Universite de Tours * du lundi 2 au jeudi 5 juillet 2001 * * http://www.li.univ-tours.fr/taln-recital-2001/ * mailto::taln2001 at univ-tours.fr * ********************************************************************** TUTORIELS (TUTORIALS): Le traitement automatique des collocations (B?atrice Daille et Geoffrey Williams) Formal Languages for Linguists: Classical and Nonclassical Models (Carlos Martin Vide) Grammaires de d?pendance formelles et th?orie Sens-Texte (Sylvain Kahane) Intex et ses applications informatiques (Max Silberztein) CONFERENCES ASSOCIEES (WORKSHOPS) Ingenierie de la Langue et handicap (Jean-Yves Antoine et Brigitte Le Pevedic) Traduction automatique et applications en grandeur r?elle (Jean Senellart) ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From pb at lpl.univ-aix.fr Fri Feb 2 16:53:49 2001 From: pb at lpl.univ-aix.fr (Philippe Blache) Date: Fri, 2 Feb 2001 17:53:49 +0100 Subject: Publication: Journal TAL Message-ID: From: Christian Jacquemin +-----------------------------------------------+ I Revue T.A.L. I I (Le traitement automatique des langues) I I I I http://www.atala.org/tal/tal.html I +-----------------------------------------------+ "Traitement automatique des langues pour la recherche d'information" Vol. 41, Num. 2, Janvier 2001 -------------- Sommaire Christian JACQUEMIN : Pr?sentation du num?ro sur le traitement automatique des langues pour la recherche d'information Patrice BELLOT, Marc EL-B?ZE : Classification locale non supervis?e pour la recherche documentaire Pierrette BOUILLON, C?cile FABRE, Pascale S?BILLOT, Laurence JACQMIN : Apprentissage de ressources lexicales pour l'extension de requ?tes B?atrice DAILLE, Jean ROYAUT?, Xavier POLANCO : ?valuation d'une plate-forme d'indexation de termes complexes Georgette DAL, Fiammetta NAMER : G?n?ration et analyse automatiques de ressources lexicales construites utilisables en recherche d'informations Gael Harry DIAS, Sylvie GUILLOR?, Jean-Claude BASSANO, Jos? Gabriel PEREIRA LOPES : Extraction automatique d'unit?s lexicales complexes : Un enjeu fondamental pour la recherche documentaire ?ric GAUSSIER, Gregory GREFENSTETTE, David HULL, Claude ROUX : Recherche d'information en fran?ais et traitement automatique des langues Diego MOLLA, Rolf SCHWITTER, Michael HESS and Rachel FOURNIER : EXTRANS, An Answer Extraction System Fiammetta NAMER : FLEMM : Un analyseur flexionnel du fran?ais ? base de r?gles Martin RAJMAN, Romaric BESANCON, Jean-C?dric CHAPPELIER : Le mod?le DSIR: Une approche ? base de s?mantique distributionnelle pour la recherche documentaire -------------- Tous les adh?rents de l'ATALA re?oivent gratuitement la revue T.A.L. Pour devenir adh?rent : http://www.atala.org/adhesion.html Vous pouvez acheter le num?ro aupr?s de Herm?s Sciences : hermes at iway.fr http://www.editions-hermes.fr/ ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From pb at lpl.univ-aix.fr Fri Feb 2 16:54:44 2001 From: pb at lpl.univ-aix.fr (Philippe Blache) Date: Fri, 2 Feb 2001 17:54:44 +0100 Subject: Appel: Phonology (GdR 1954) Message-ID: From: Jean-Pierre Angoujard A DIFFUSER TRES LARGEMENT / PLEASE POST APPEL A COMMUNICATION / CALL FOR PAPERS 3?me JOURN?ES INTERNATIONALES DU GDR " PHONOLOGIE " 3rd INTERNATIONAL PHONOLOGY MEETING OF THE GDR 1954 NANTES / FRANCE 30 mai ? 1er juin 2001 / 2001 May 30th ? June 1st Le Groupe de recherche en phonologie (GDR 1954) du C.N.R.S. organise ses 3?me Journ?es Internationales ? Nantes. Vous ?tes invit?s ? proposer des contributions dans tout domaine en rapport avec la phonologie (30 min. de pr?sentation et 10 min. de discussion). The research group (GDR) in phonology of the French National Center for Scientific Research (C.N.R.S.) invites submissions for its 3rd International Phonology Meeting (30 min. presentation plus 10 min. discussion). Scope : any topic related to phonology. Les auteurs sont invit?s ? soumettre un r?sum? anonyme (2 pages A4 maximum). Les noms et adresses des auteurs devront appara?tre sur une feuille s?par?e. Authors are invited to submit an anonymous abstract not exceeding 2 A4 or US quarto pages. Authors? names and addresses should be sent on a separate page. LANGUES / WORKING LANGUAGES : fran?ais et anglais / English and French DATES A RETENIR / IMPORTANT DATES : Date limite de soumission / Deadline for submission : 25 mars 2001 / 2001 March 25th Notification des acceptations / Notification to authors : 27 avril 2001 / 2001 April 27th COMITE NATIONAL / NATIONAL COMMITTEE J.-P. ANGOUJARD (Universit? de Nantes) G. BERGOUNIOUX (Universit? d?Orl?ans) N. CLEMENTS (CNRS, Paris) J. DURAND (Universit? de Toulouse 2) B. LAKS (Universit? Paris 10) COMITE SCIENTIFIQUE / SCIENTIFIC COMMITTEE F. DELL (CNRS, Paris) D. HIRST ( CNRS, Aix-en-Provence) M. KLEIN (Universit? Paris 10) M. KENSTOWICZ (MIT) J. LOWENSTAMM (Universit? Paris 7) Ch. LYCHE (Oslo / TromsO) M. PLENAT (CNRS, Toulouse) P. SAUZET (Universit? Paris 8) N. VALLEE (ICP, Grenoble) S. WAUQUIER-GRAVELINES (Universit? de Nantes) ORGANISATION / ORGANISERS Jean-Pierre ANGOUJARD ; Sandrine FERR? ; Delphine POURIN. Equipe " Acoustique, Acquisition et Interpr?tation " (AAI, JE 2220), Universit? de Nantes : Les propositions de communications doivent ?tre envoy?es ? Jean-Pierre ANGOUJARD, soit par courrier postal soit par courrier ?lectronique (recommand?). Please send submissions to Jean-Pierre ANGOUJARD (electronic submissions is recommended) : Jean-Pierre Angoujard " Acoustique, Acquisition et Interpr?tation " Facult? des Lettres et Sciences Humaines Chemin de la Censive-du-Tertre BP 81227 44312 NANTES Cedex 3 France m?l / e-mail : jean-pierre.angoujard at humana.univ-nantes.fr ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From pb at lpl.univ-aix.fr Mon Feb 5 11:11:22 2001 From: pb at lpl.univ-aix.fr (Philippe Blache) Date: Mon, 5 Feb 2001 12:11:22 +0100 Subject: LN: Passage de temoin (New editor) Message-ID: From: "Philippe Blache" Chers collegues, Ceci est mon dernier envoi sur la liste LN en tant que moderateur : c'est desormais Alexis Nasr (alexis.nasr at lim.univ-mrs.fr) qui assurera l'edition de cette liste, en collaboration avec Thierry Hamon (Thierry.Hamon at lipn.univ-paris13.fr). Je remercie grandement Alexis d'avoir accepte de prendre en charge cette tache. LN est un outil d'information extremement important pour notre communaute. Je suis tres heureux d'y avoir contribue et je suis certain qu'un nouveau dynamisme saura lui etre insufle par Alexis et Thierry. Cordialement, Philippe ---------------- For those of you who don't understand French: the new LN editor is Alexis Nasr (alexis.nasr at lim.univ-mrs.fr). Thank you for your interest in LN ! --------------------------------------------------------------------------- Philippe Blache | tel: +33 (0)442.95.36.36 LPL - Universite de Provence | fax: +33 (0)442.59.50.96 29, Avenue Robert Schuman | 13621 Aix-en-Provence | email: pb at lpl.univ-aix.fr France | http://www.lpl.univ-aix.fr/~blache --------------------------------------------------------------------------- ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Mon Feb 12 17:22:49 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Mon, 12 Feb 2001 18:22:49 +0100 Subject: Jobs: Pre- and Postdoctoral Fellowships DFKI Message-ID: From: Hans Uszkoreit Industry Host R&D Fellowships in the Prestigious Marie Curie Programme Pre- and Postdoctoral Fellowships for applicants from EU Member States and Associated Countries in: Multilingual Information Retrieval Agent Technologies Information Management Content Analysis Text Generation A cooperation between DFKI, Saarbruecken and Innoserve Media Solutions GmbH Details: http://www.dfki.de/~hansu/nice-job-offer.pdf ________________________________________ Prof. Dr. Hans Uszkoreit Scientific Director at DFKI http://www.coli.uni-sb.de/~hansu/ Email: Uszkoreit at dfki.de ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Mon Feb 12 17:23:14 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Mon, 12 Feb 2001 18:23:14 +0100 Subject: ATALA: journee du 28 avril Message-ID: From: Benoit Habert ------------------------------------------- JOURNEES de l'ATALA - APPEL A COMMUNICATION ------------------------------------------- Samedi 28 avril 2001 De la langue aux genres et aux types La place des types et des genres textuels dans la description et le traitement automatique d'une langue peut ?tre reconsid?r?e aujourd'hui ? la lumi?re des corpus et des annotateurs automatiques disponibles mais aussi de l'exp?rience gagn?e ? traiter non plus des domaines restreints mais du texte "tout venant", en tr?s grande quantit?. Cependant la notion de texte tout-venant doit sans doute ?tre r??labor?e ou d?pass?e. La notion de genre textuel est peu ?tudi?e en linguistique. Elle suscite des d?bats sur sa d?finition et son op?rativit? (Adam 00). N?anmoins, de nombreux travaux (Bronckart 96, Roulet 96) portent sur les genres et leur place dans l'?conomie des ?changes langagiers. L'hypoth?se sous-jacente est que les genres organiseraient et r?guleraient l'infinie diversit? des ?nonc?s (Bakhtine). Ma?triser une langue, ce serait d'abord ma?triser des genres. Ces travaux se trouvent aujourd'hui en mesure, gr?ce ? la multiplication des corpus et des outils d'annotation, de tester effectivement ces hypoth?ses. On peut ainsi chercher ? qualifier les diff?rences significatives entre les genres pr?d?finis d'un corpus donn? et tester la pertinence du classement initial des documents de ce corpus en fonction de ces genres. On peut ?galement, dans une approche d'apprentissage non supervis?, d?velopper une typologie inductive des textes en les caract?risant par un ensemble de dimensions organisant des traits linguistiques (Biber 88, 95). Le traitement automatique des langues fait de plus en plus appel ? de volumineux corpus textuels pour l'acquisition des connaissances qui lui sont n?cessaires : cadres de sous-cat?gorisation des verbes, collocations, encha?nement de cat?gories, acquisition de cat?gories s?mantiques... L'obstacle actuel n'est donc plus la disponibilit? de corpus, mais l'h?t?rog?n?it? des donn?es qui sont rassembl?es sous ce nom. En effet la qualit? des connaissances acquises d?pend directement de la ma?trise des caract?ristiques du corpus utilis?, qu'il s'agisse de l'?tiquetage morphosyntaxique (Biber 93), du parsage (Sekhine 97) ou de la recherche d'information (Karlgren 98). Il importerait alors de (re)conna?tre les types de textes ou les genres pr?sents dans les corpus utilis?s. Les propositions de communication pourront en particulier apporter une contribution sur les questions et les th?mes suivants : . Le profilage de documents : comment r?partir un ensemble donn? de documents en sous-ensembles homog?nes pour les traitements automatiques envisag?s ? . L'influence des genres ou des types de textes sur les performances des traitements automatiques : y a-t-il des t?ches plus sensibles que d'autres ? l'h?t?rog?n?it? des donn?es utilis?es ? . Retrouve-t-on d'un domaine ? un autre des genres ou des types similaires ? . Quelle est la fiabilit? d'une r?partition d'un ensemble de documents en genres et en types par un ensemble d'individus ? . La description syntaxique et s?mantique d'une langue, y compris pour le TAL, doit-elle prendre en compte la variation en genres ? . Les "genres" reconnus dans une communaut? langagi?re donn?e sont-ils identifiables de mani?re automatique ? . Les "genres" reconnus dans une communaut? langagi?re donn?e constituent-ils les bonnes "variables" pour expliquer l'h?t?rog?n?it? d'un corpus ? Soumission (modalit?s) Un r?sum? de deux ? quatre pages doit ?tre envoy? avant le 28 f?vrier 2001 par courrier ?lectronique uniquement ? : Fran?ois Rastier (lpe2 at ext.jussieu.fr) et ? Beno?t Habert (habert at limsi.fr) Les notifications d'acceptation seront donn?es pour le 31 mars 2001 Pour plus d'informations sur l'ATALA et sur l'organisation des journ?es d'?tudes, consultez le site de l'ATALA ? l'adresse: http://www.atala.org -- La France est le "pays-de-l'amour-et-des-fleurs", disent gentiment les Japonais. Quel ?trange sentiment, non d?nu? de r?verie, que de se d?couvrir "has been". Fran?ois Julien et Thierry Marchaisse, Penser d'un dehors (la Chine). Entretiens d'extr?me-Occident, Seuil, 2000, p. 490-491. Beno?t Habert Equipe Langues Interpr?tation Repr?sentations (LIR) - LIMSI, BP 133, F-91403, Orsay C?dex & universit? Paris X mailto:habert at limsi.fr http://www.limsi.fr/Individu/habert/ Tel : mardi et jeudi (33 1) 69 85 80 22 (fax 80 88) - lundi et vendredi (33 1) 40 97 47 34 (fax 40 73) - Fax (33 1) 45 34 35 76 ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Mon Feb 12 17:23:38 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Mon, 12 Feb 2001 18:23:38 +0100 Subject: Conf: TALN 2001 workshop on Machine Translation Message-ID: CALL FOR PARTICIPATION Workshop on Machine Translation "Machine Translation and Large-Scale Applications" 5 July 2001 in conjunction with TALN'2001(2-5 July 2001) TOURS Europe - FRANCE Submission deadline : 15 april 2001 MOTIVATION Against the backdrop of an increasingly multilingual society, the Machine Translation Workshop of TALN'2001 looks at the main challenges to Machine Translation and multilingual NLP. Indeed, MT has seen a remarkable development for the past few years in terms of the number of translation requests (about a million translation requests everyday on the Web) as well as in terms of the different types of formats translated : translation of dynamic resources(FAQ, Web pages, daily papers), emails, requests for search engines, etc. These different types of translations demand different levels of quality, and induce an important associated feedback in the form of additional bilingual dictionaries. At the same time there is a growing need for more specialized translation. For this "specialization" the construction of wide-covering mutlilingual resources is an essential component of this more demanding translation. Because of the increase of the number of contributors (experts or users), the questions of exchange, reusability and incrementability of the translation resources had to be raised. The associated investment (public or private) lead to a general tendency to initiate centralizations (cf. Elra), standards (ISO 12220), transfer formalisms (OLIF), and more generally, to create mutlilingual data exchange formats (UNL). In any case, the choice of a linguistic data support cannot be separated from pragmatic considerations concerning the scale, the volume of additional resources becoming more important than the generic resources. These resources can vary from "simple" terminological resources (aligned lexicons) to more complex resources such as terminological grammars, transfer dictionaries, and graphs/grammars of translation. FOCUS OF THE WORKSHOP The focus of the workshop is not only recent machine translation research and products, but also the latest developments in multilingual language technology. The workshop aims at considering the questions of the construction, the validation and the utilization of large-scale resources applied to machine translation. The papers submitted can be related to the different topics below, but also to some other closely related topics : - use of standardization formalisms on important volumes of data - evaluation and realization of construction tools of such resources (from corpus, monolingual resources...) - integration and conversion of existing resources - validation and "expert" improvement processes - massive parallel acquisition of terminology in the framework of a network of users - management of mutlilingual resources compared to bilingual resources - multilingual extraction and machine translation QUESTIONS AND ISSUES You can either submit an abstract of 5 pages, or a complete version of your paper(up to 10 pages). Submitted papers should be in French or in English (for non French speakers). The abstracts and the papers submitted should conform to the submission format of TALN'2001 (style sheets are available on the TALN'2001 site http://www.li.univ-tours.fr/taln-recital-2001) : Times 12, single-spaced, 10 pages at the most, including figures, examples and references. Authors should send their submission as a file attached to an e-mail (ps, pdf, rtf files, A4 format) at the following e-mail address : workshop-taln at systran.org The e-mail should contain the following information: submission title, authors' names and affiliation. Submissions will be reviewed by two experts of the Program Comittee. The final version of the accepted papers will be published in the workshop proceedings. The papers will give rise to 20 minute presentations followed by 10 minutes of questions. PROGRAM COMITTEE Christian Boitet, CLIPS-IMAG,equipe GETA, Grenoble http://clips.imag.fr/geta Maurice Gross, LADL & UMLV, Marne-la-Vallee Igor Boguslavskij, IPPI PAN, Moscou Georges Carayannis, ELRA & ILSP, Athen Joseph Dichy, Faculte des Langues, Universite Lyon II Pierre-Yves Foucou, SYSTRAN, Paris http://www.systransoft.com Daniel Grasmick, SAP, Waldorf Jean Senellart, SYSTRAN, Paris http://www.systransoft.com Tamas Varadi, Linguistics Institute, Hungarian Academy of Sciences Remi Zajac, CRL/NMSU, Las Cruces, http://crl.nmsu/edu/~rzajac IMPORTANT DATES Submission deadline: 15/04/2001 Notification to authors: 25/04/2001 Final version due (camera-ready) : 15/05/2001 Workshop : 05 July 2001 =========================================================================== ============ APPEL A COMMUNICATION Atelier sur la Traduction Automatique "Traduction automatique et applications en grandeur reelle" le 5 juillet 2001 organise dans le cadre de TALN'2001 (2-5 juillet 2001) TOURS - FRANCE Date limite de soumission : 15 avril 2001 MOTIVATION Dans le contexte d'une societe de plus en plus multilingue, l'Atelier sur la Traduction Automatique de TALN'2001 s'interesse aux principaux defis de la Traduction Automatique et du TAL multilingue. En effet, la Traduction Automatique a connu ces dernieres annees un essor considerable, tant en volume d'utilisation (de l'ordre du million de requetes de traduction quotidiennes sur Internet), qu'en etendue : traduction de ressources dynamiques (FAQ, pages web, quotidiens), de mails, de requetes pour moteurs de recherche... Ces traductions, pour lesquelles les exigences de qualite sont variables, induisent un volume de feedback associe tres important en valeur absolue se presentant sous la forme de dictionnaires additionnels bilingues. Parallelement s'etablit une demande croissante pour des traductions specialisees. Pour cette "specialisation", la constitution de ressources multilingues a large couverture est une composante essentielle d'une traduction pour laquelle l'exigence est beaucoup plus importante. De l'augmentation du nombre d'intervenants (experts ou utilisateurs) decoulent naturellement les questions d'echange, de reutilisation, d'incrementabilite de ces ressources de traduction. L'investissement associe (tant d'un point de vue prive que public), a conduit a une tendance generale pour l'etablissement d'initiatives de centralisation (cf Elra), de normes (ISO 12220), de formalismes de transfert (OLIF), ou de maniere plus generale, de formats d'echange d'information multilingue (UNL). Dans tous les cas, le choix du support de l'information linguistique ne peut etre dissocie de considerations pragmatiques d'echelle, le volume des ressources additionnelles devenant plus important que celui des ressources generiques. Ces ressources pouvant aller de ressources terminologiques "simples" (dictionnaires alignes), a des ressources plus complexes comme des grammaires terminologiques, dictionnaires de transfert, et graphes/grammaires de traduction. CENTRES D'INTERET DE L'ATELIER Les centres d'interet de l'atelier concernent non seulement la recherche en traduction automatique et les produits, mais egalement les developpements multilingues recents en TAL. Cet atelier vise a developper une reflexion autour des questions de constitution, de validation, et d'utilisation de ressources a large couverture en traduction automatique. Les articles proposes pourront en particulier aborder les points suivants, mais aussi tout probleme connexe : - utilisation de formalismes de normalisation sur des grands volumes de donnees - evaluation et realisation d'outils de construction de telles ressources (a partir de corpus, de ressources monolingues...) - integration et conversion de ressources existantes - validation et processus d'enrichissement "expertise" - acquisition parallele massive de terminologie dans le cadre d'un reseau d'utilisateurs - gestion de ressources multilingues comparees a celles de ressources bilingues - extraction multilingue et traduction automatique PRECISIONS Vous pouvez soit soumettre un resume de 5 pages, soit une version complete de votre article (jusqu'a 10 pages). Les articles soumis doivent etre ecrits en francais ou en anglais (pour les non-francophones). Les resumes et les articles doivent correspondre au format de TALN'2001 (des feuilles de style sont disponibles sur le site de TALN'2001 http://www.li.univ-tours.fr/taln-recital-2001) : Times 12, interligne simple, 10 pages au maximum, figures, exemples et references comprises. Les auteurs enverront leur resume ou leur article en fichier attache (ps, pdf, rtf au format A4) a l'adresse email suivante : workshop-taln at systran.org L'email contiendra les informations suivantes : titre de la soumission, nom de l'auteur, affiliation. Les resumes et articles soumis seront evalues par deux experts du Comite de Programme. La version finale des articles acceptes sera publiee dans les actes de l'Atelier. Les communications donneront lieu a une presentation de 20 minutes et seront suivies de 10 minutes de questions. COMITE DE PROGRAMME Christian Boitet, CLIPS-IMAG,equipe GETA, Grenoble http://clips.imag.fr/geta Maurice Gross, LADL & UMLV, Marne-la-Vallee Igor Boguslavskij, IPPI PAN, Moscou Georges Carayannis, ELRA & ILSP, Athen Joseph Dichy, Faculte des Langues, Universite Lyon II Pierre-Yves Foucou, SYSTRAN, Paris http://www.systransoft.com Daniel Grasmick, SAP, Waldorf Jean Senellart, SYSTRAN, Paris http://www.systransoft.com Tamas Varadi, Linguistics Institute, Hungarian Academy of Sciences Remi Zajac, CRL/NMSU, Las Cruces, http://crl.nmsu/edu/~rzajac Date limite de soumission : 15/04/2001 Notification aux auteurs : 25/04/2001 Version finale (prete a la reproduction) : 15/05/2001 Atelier : 5 juillet 2001 ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Mon Feb 12 17:21:58 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Mon, 12 Feb 2001 18:21:58 +0100 Subject: Publications: Revue de semantique et pragmatique Message-ID: From: "Francois NEMO" Revue de Semantique et Pragmatique ISSN 1285-4093 Numero 8, 2000 http://www.univ-orleans.fr/PUO/RSP/ TITRE: Imperatif, indicatif et subjonctif : de la morphologie a l'interaction AUTEUR(S): Daniel Luzzati PAGE(S): 7-27 TITRE: Pour une approche linguistique ET discursive de l'organisation informationnelle AUTEUR(S): Anne Grobet PAGE(S): 29-42 TITRE: A propos de quelques actes ``pseudo-directifs'' de la communication ecrite AUTEUR(S): Giuseppe Manno PAGE(S): 43-62 TITRE: Par terre vs sur le sol AUTEUR(S): S.-N. Kwon-Pak PAGE(S): 63-79 TITRE: Discourse particles, turn-taking, and the semantics-pragmatics interface AUTEUR(S): Kerstin Fischer PAGE(S): 81-100 TITRE: Le fonctionnement de la conjonction mais dans le dialogue romanesque AUTEUR(S): Isabelle Daussaint-Doneux PAGE(S): 101-119 TITRE: Temporality and causality: The case of Greek subordinating connectives AUTEUR(S): Eliza Kitis PAGE(S): 121-141 TITRE: Adverbes iteratifs et quantification AUTEUR(S): Francis Renaud PAGE(S): 143-168 Compte rendu TITRES: 1) Une histoire du point de vue 2) La construction textuelle du point de vue AUTEUR: Alain Rabatel Lecteur: Eric Beaumatin Merci d'excuser les doubles envois ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Mon Feb 12 17:22:32 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Mon, 12 Feb 2001 18:22:32 +0100 Subject: Appel: TALN 2001 Message-ID: ********************************************************************** * * TALN 2001 * Traitement Automatique du Langage Naturel * * Universite de Tours * du lundi 2 au jeudi 5 juillet 2001 * * http://www.li.univ-tours.fr/taln-recital-2001/ * mailto::taln2001 at univ-tours.fr * ********************************************************************** (see English version below) ********** TALN 2001 : 3eme APPEL A COMMUNICATION ********** ----> DATE LIMITE DE SOUMISSION : VENDREDI 23 FEVRIER 2001 <---- TALN 2001 aura lieu a Tours du lundi 2 au jeudi 5 juillet 2001, organise par le LI (Laboratoire d'Informatique de l'Universit? de Tours) et l'axe LTI (Langues et Technologies de l'information). La conference TALN 2001 comprendra des communications scientifiques, des conferenciers invites, des seances de demonstration et posters, ainsi que des tutoriels. Les langues officielles de la conference sont le francais et l'anglais. TALN 2001 est organisee sous l'egide de l'ATALA (Association pour le Traitement Automatique des LAngues) et se tiendra conjointement a la conference pour jeunes chercheurs RECITAL 2001 (appel a communications a paraitre separement). ********** THEMES ********** Les communications pourront porter sur tous les themes habituels du TALN, incluant, de facon non limitative: lexique morphologie syntaxe semantique pragmatique discours analyse generation resume dialogue traduction automatique approches logiques, symboliques et statistiques TALN 2001 souhaite egalement accueillir des travaux de domaines proches dans lesquels le TALN joue un role important, dans la mesure ou l'accent est mis sur la composante TALN : traitement de la parole (prosodie, linguistique, pragmatique) traitement de l'ecrit aspects cognitifs terminologie acquisition de connaissances a partir de textes extraction d'information recherche documentaire linguistique de corpus linguistique mathematique utilisation d'outils de TALN pour la modelisation linguistique enseignement assiste, enseignement des langues. Sont aussi attendus des travaux sur des applications du TALN, implementees et evaluees, faisant ressortir leurs aspects scientifiques et les enseignements tires. Des demonstrations de systemes pourront etre proposees, independamment ou en complement d'articles scientifiques. L'emploi du temps de la conference comprendra une session pour ces demonstrations. ********** CALENDRIER ********** ----> DATE LIMITE DE SOUMISSION : VENDREDI 23 FEVRIER 2001 <---- Notification aux auteurs : vendredi 27 avril 2001 Version finale (pret-a-clicher) : vendredi 11 mai 2001 Conference : du lundi 2 au jeudi 5 juillet 2001 ********** MODALITES DE SOUMISSION ********** Les articles soumis seront rediges en francais (ou en anglais par les non-francophones). Ils ne devront pas depasser 10 pages en Times 12, espacement simple, figures, exemples et references compris. Les soumissions devront parvenir au comite d'organisation avant le 23 fevrier 2001, sous forme electronique, a mailto:taln2001 at univ-tours.fr. En cas d'impossibilite d'envoi par courrier electronique, une soumission "papier" pourra etre admise. Dans ce cas, trois exemplaires devront etre envoyes a l'adresse suivante: TALN 2001 LI (Laboratoire d'Informatique de l'Universite de Tours) E3i, 64, avenue Jean Portalis 37200 Tours France ********** FORMAT DES SOUMISSIONS ********** Les auteurs devront envoyer leur soumission par courrier electronique sous la forme d'un document attache (fichiers ps ou pdf au format A4 et non Lettre US). Le message contiendra le titre de la soumission et les noms des auteurs. Les formats a utiliser pour la redaction sont disponibles sur le site de la conference: http://www.li.univ-tours.fr/taln-recital-2001. ********** CRITERES DE SELECTION ********** Les auteurs sont invites a soumettre des travaux de recherche originaux, n'ayant pas fait l'objet de publications anterieures. Les soumissions seront examinees par au moins deux specialistes du domaine. Seront considerees en particulier : L'importance et l'originalite de la contribution, La correction du contenu scientifique et technique, La discussion critique des resultats, en particulier par rapport aux autres travaux du domaine, La situation des travaux dans le contexte de la recherche internationale, L'organisation et la clarte de la presentation, L'adequation aux themes de la conference. Les articles selectionnes seront publies dans les actes de la conference. ********** DEMONSTRATIONS ET POSTERS ********** Une ou deux seances specifiques seront prevues pour des demonstrations (presentations logicielles) et des posters (85 x 120 cm). Les propositions de demonstration ou de poster suivent les memes regles que les soumissions de communication mais ne devront pas depasser 4 pages. ********** PRESENTATIONS ORALES ********** Les presentations orales dureront 20 minutes et seront suivies de 10 minutes de questions. Il sera possible d'utiliser un retro-projecteur ou un video-projecteur. ********** ACTES ********** Les actes de la conference seront distribues a tous les participants. Le Comite de redaction de la revue Traitement Automatique des Langues (t.a.l.) s?lectionnera deux articles pour publication. ********************************************************************** * * ENGLISH VERSION * ********************************************************************** ********** TALN 2001 : 3rd CALL FOR PAPERS ********** ----> SUBMISSION DEADLINE: FRIDAY, 2/23/2001 <---- TALN 2001 will be held at Tours on July, 2 - 5 2001, organized by the LI (Computer Laboratory of Tours University) and LTI (Language and Information Technologies). The conference includes paper presentations, invited speakers, tutorials and software demonstrations. The official conference languages are French and English. TALN 2001 is organized in collaboration with ATALA (Association pour le Traitement Automatique des LAngues) and will be held jointly with the young researcher conference RECITAL 2001 (a separate call for papers will follow). ********** TOPICS ********** Papers are invited in all areas of NLP, including (but not limited to): lexicon morphology syntax semantics pragmatics discourse parsing generation abstraction/summarisation dialogue translation logical, symbolical and statistical approaches TALN 2001 also invites contributions in fields for which NLP plays an important role, as long as these contributions emphasize their NLP dimension : speech processing text processing cognition terminology knowledge acquisition information retrieval documentary research corpus-based linguistics mathematical linguistics management and acquisition of linguistic resources computer assisted learning NLP tools for linguistic modelization TALN 2001 also welcomes submissions focusing on NLP applications that have been implemented, tested and evaluated and emphasizing the scientific aspects and conclusions drawn. Software demonstrations can be proposed, either independently or in connection with a paper proposal. Specific sessions for the demos will be scheduled in the conference. ********** CALENDAR ********** ----> SUBMISSION DEADLINE: FRIDAY, 2/23/2001 <---- Notification to authors: 4/27/2001 Final version due (camera-ready): 5/11/2001 Conference : 7/2-5/2001 ********** SUBMISSION PROCEDURE ********** The maximum length for papers is 10 pages, in Times 12, single spaced, including figures, examples and references. Electronic submissions must reach the organizing committee before 2/23/2001, sent to mailto:taln2001 at univ-tours.fr. If electronic submission is not possible, 3 hard-copies of the paper must reach the organizing committee before 2/23/2001, at the following address: TALN 2001 LI (Laboratoire d'Informatique de l'Universite de Tours) E3i, 64, avenue Jean Portalis 37200 Tours France ********** FORMAT FOR SUBMISSIONS ********** Authors should send their submission as a file attached to an e-mail(ps or pdf files, A4 format and not US Letter format), containing the following informations: submission title and author's names. The formats that MUST be used are available on the Conference web site: http://www.li.univ-tours.fr/taln-recital-2001/ . ********** SELECTION CRITERIA ********** Authors are invited to submit original, previously unpublished work. Submissions will be reviewed by at least 2 specialists of the domain. Decisions will be based on the following criteria : Importance and originality of the paper Accuracy of the scientific and technical content Comparison of the results obtained with other relevant work Layout and clarity of the paper Relevance to the topics of the conference Accepted papers will be published in the proceedings of the conference. ********** DEMOS AND POSTERS ********** One or two specific sessions for the demos and the posters (85 x 120 cm) will be scheduled in the conference. The demo or poster submissions accord to the same rules of paper submission, BUT they should not exceed 4 pages. ********** TALKS ********** Papers should be of 20 minutes duration. 10 minutes will be left for questions. It will be possible to use a overhead projector or a video-projector. ********** PROCEEDINGS ********** The conference proceedings will be given to all participants. The editorial staff of the journal Traitement Automatique des Langues (t.a.l.) will select two papers for publication. ********** COMITE DE PROGRAMME ********** ********** PROGRAMME COMMITTEE ********** (le comite de programme sera entoure d'un large comite de lecture) (the program committee will be supervised by a broad reviewing committee) Pascal Amsili, TALaNa Frederic Bechet, LIA Philippe Blache, LPL Christian Boitet, CLIPS-GETA Pierrette Bouillon, ISSCO Beatrice Daille, IRIN Laurence Danlos, LORIA/TALaNa Claire Gardent, LORIA Eric Laporte, CERIL Denis Maurel, LI (president) Piet Mertens, CCL Jean-Marie Pierrel, LORIA Martin Rajman, EPFL Owen Rambow, ATT Labs-Research Jacques Siroux, IRISA LLI/CORDIAL Jean Veronis, LPL Pierre Zweigenbaum, DIAM ********** COMITE D'ORGANISATION ********** ********** ORGANIZING COMMITTEE ********** Claire Agafonov, LTI Beatrice Bouchou, LI Alain Cambourian, LTI Alain Delplanque, LTI Nathalie Friburger, LI Nathalie Garric, LTI Paul Gaudin, LTI Manuel Gonzales de Avila, Ciremia Thierry Grass, LTI Denis Maurel, LI (president) Nathalie Rossi, LTI Mohamed Slimane, LI Nicole Vincent, LI ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Thu Feb 15 17:45:55 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Thu, 15 Feb 2001 18:45:55 +0100 Subject: Jobs: 4 offres Message-ID: 1/ From: Mari Olsen Subject: Jobs: Microsoft Natural Language Group 2/ From: Joanne Samuelson Subject: Wordstream, Inc. career opportunity 3/ From: Jean Pierre Chanod Subject: 2 postes de chercheur en s?mantique; 2 research positions in semantics: 4/ From: Jean Pierre Chanod Subject: Post-Doc - MultiLingual Theory and Technologies ------------------------------------------------------------------------------ 1/ From: Mari Olsen Subject: Jobs: Microsoft Natural Language Group Send applications/questions to nljobs at microsoft.com. -Mari Broman Olsen Computational Linguist - French Primary responsibilities include enhancing and extending the French computational grammar and grammar-checking system, in accordance with the overall architecture of the Microsoft Natural Language Understanding system. The initial emphasis will be on understanding the output of the syntactic component. Native French language proficiency and an advanced degree in Linguistics, Computer Science, or a closely related discipline are required. Other desirable qualifications include experience in linguistic research, with an emphasis on syntax, semantics, or discourse analysis; familiarity with Natural Language Processing; a flexible approach to linguistic theory; practical experience with software development and NLP implementation issues. Linguistic Test Engineer - Spanish Primary responsibility is the creation and maintenance of linguistic test data for Microsoft's Spanish Natural Language Processing system. Responsibilities include analyzing a corpus in Spanish and creating expected linguistic output based on a specification, evaluating linguistic coverage, reporting accuracy, finding and tracking linguistic bugs, and measuring improvement of the products and technology. Native Spanish language proficiency and bachelor's degree in Linguistics or Computational Linguistics required; a master's or doctorate degree strongly preferred. Other qualifications include demonstrated skill in detailed linguistic analysis, with an emphasis on syntax or semantics; general investigative and problem-solving skills; and an ability to track details. General knowledge of personal computers, and the ability to install, upgrade and use Microsoft applications and operating system(s) are desirable. Computational Linguist - Semanticist Enhance, develop, and ship technology in important new problem domains, including information retrieval, information extraction, generation, and natural language command & control of applications, all of which require an integrated understanding of computational semantics. Candidates are welcomed from a broad variety of disciplines and backgrounds, for example, with expertise in any of the following areas: statistical approaches to problems like word sense disambiguation or word correlation; knowledge-based techniques involving semantic networks or ontologies; computational approaches to "dynamic" semantic theories like DRT, Dynamic Montague Grammar or Context/File Change Semantics; inter alia. Qualified applicants should have an advanced degree in Linguistics, Computational Linguistics, or CS (or equivalent experience), strong coding skills, and a desire to see their ideas through to the product stage. ------------------------------------------------------------------------------ 2/ From: Joanne Samuelson Subject: Wordstream, Inc. career opportunity Director of Language Development, Computational Linguist Opportunity to join an exciting young company with a creative approach to language translation. WordStream isn?t trying to be another Machine Translation company but rather has redefined the problem and is solving it with a unique technology based on an Interlingua. Competitive salary and benefits. Metropolitan Boston location. Job Description: Computational linguist to lead development and design of commercial interlingua MT system and to manage a team of linguists. The job will involve determining the conceptual framework for the development of a lexical database and grammar system. Candidate will need to work closely with Software Development team to ensure coordination of linguistic and technical requirements. Job Requirements: Master?s (PhD preferred) in Computational Linguistics or related areas. Fluent in English and at least one other language, preferably one of the following: German, French, Spanish, Italian, Japanese or Chinese. Excellent communication skills as well as the ability to both motivate a team and be a team player. Highly Desirable: Experience with commercial MT systems along with project management and implementation of MT applications. Experience managing linguists and technology specialists. Familiarity with linguistic resources (corpora, grammars, parsers, etc.). Programming skills (knowledge of perl, java, or C++). Experience in grammar and lexicon development. Interested parties should contact : www.wordstream.com careers at wordstream.com WordStream Inc. 48 Grove St. Suite 201 Somerville MA 02144 Tel 617-666-7700 X231 Fax 617-666-2850 ------------------------------------------------------------------------------ 3/ From: Jean Pierre Chanod Subject: 2 postes de chercheur en s?mantique; 2 research positions in semantics: XRCE-Grenoble (Xerox Research Centre Europe) est sp?cialis? dans la recherche en traitement automatique des langues, en syst?mes distribu?s, et en gestion de la connaissance. Ce laboratoire travaille en association ?troite avec les autres laboratoires de Xerox ? Cambridge et Palo Alto (PARC). MLTT (the MultiLingual Theory and Technology Group) a deux postes ? pourvoir pour des chercheurs dans le domaine du traitement s?mantique de textes. En collaboration avec le groupe de recherche, les candidats devront conduire des recherches et d?velopper des m?thodes pour repr?senter le contenu s?mantique des textes, fusionner ces contenus avec des informations externes (telles que des ontologies), et enfin effectuer des raisonnements sur les repr?sentations ainsi g?n?r?es. Ces techniques seront appliqu?es ? des t?ches telles que l'extraction de connaissance sur des textes tout venant. Qualifications: Les candidats devront avoir un doctorat ou ?quivalent dans l'une des disciplines suivantes: linguistique, math?matique, informatique. Une exp?rience en traitement automatique des langues est souhaitable. La ma?trise de la langue anglaise, parl?e et ?crite, est requise. XRCE offre d'excellents salaires ainsi que divers avantages sociaux, un bon environnement informatique et la possibilit? de travailler pour un centre international de recherche leader dans son domaine. Le lieu de travail est situ? ? Grenoble (France), au pied des Alpes (snowboard, ski, golf, randonn?e, kayak, parapente, escalade, p?che etc.). Les pages WEB (http://www.xrce.xerox.com) sont ? votre disposition pour de plus amples informations sur le centre. Les postes sont ? dur?e ind?termin?e, et ouverts d?s maintenant. Les candidatures dans le cadre d'un sabbatique sont ?galement les bienvenues. Les demandes devront inclure la r?f?rence MLTT010207 et devront ?tre envoy?es ? l'adresse suivante: Mr. Christophe Mitenne Ressources Humaines Xerox Research Centre Europe 6, chemin de Maupertuis 38240 MEYLAN, France English version: XRCE Grenoble Laboratory is a world leader in natural language, distributed systems, and knowledge management research. It forms an integral part of Xerox's research culture with sister laboratories in Cambridge (UK) and Palo Alto (PARC, California). The MultiLingual Theory and Technology Group has two open positions for researchers in semantic processing of natural language texts. In collaboration with a group of researchers, the candidates will investigate and elaborate state-of-the-art techniques for representing the contents of natural language texts, for merging these contents with background information (such as ontologies) and for performing some reasoning on the basis of such representations. The resulting techniques will be applied to tasks such as knowledge extraction from unrestricted texts. Research Focus & Qualifications: Applicants should hold a Ph.D. degree or equivalent in a relevant discipline e.g. computer science, linguistics, mathematics etc. Hands-on experience with applying a wide range of NLP techniques is also desirable. Proficiency in English is required. XRCE offers excellent salaries and benefits (and relocation package), excellent computing facilities and the opportunity to work in a leading international research institute. The successful candidates will be located in Grenoble (France), in the foothills of the Alps, providing access to some of the best outdoors in the world (activities in this region include: snowboarding, skiing, golfing, hiking, kayaking, paragliding, rock climbing, fishing etc.). Please refer to the XRCE webpages (http://www.xrce.xerox.com) for further information regarding this position and on our research centre. The positions are permanent and are open now. Applications for sabbaticals are also welcomed. Applications should include the reference MLTT010207 and should be sent to following address: Mr. Christophe Mitenne Human Resources Xerox Research Centre Europe 6, chemin de Maupertuis 38240 MEYLAN, France -------------------------------------------------------------------------- 4/ From: Jean Pierre Chanod Subject: Post-Doc - MultiLingual Theory and Technologies Ref: MLTT/010208 XRCE Grenoble Laboratory is a world leader in natural language, distributed systems, and knowledge management research. It forms an integral part of Xerox's research culture with sister laboratories in Cambridge (UK) and Palo Alto (PARC, California). The MultiLingual Theory and Technology Group has an open position for a post-doc, for a duration 18 months, starting in May 2001. In collaboration with a small group of other researchers, the candidate will elaborate state-of-the-art robust language components for English, based on our new system for text analysis and on existing language resources. The primary focus is on expanding our English dependency grammar, with a view of applying it to higher-level linguistic processes (coreference, word sense & structural disambiguation,s paraphrase, mapping onto knowledge representation). Those linguistic components will be used and tested in a number of large-scale applications, such as knowledge extraction in genomics. Research Focus & Qualifications: Applicants should hold a Ph.D. degree or equivalent in a relevant discipline e.g. computer science, linguistics, mathematics etc. Hands-on experience with applying NLP techniques to real texts is a must.The candidate should be a native speaker of English. XRCE offers competitive salaries, excellent computing facilities and the opportunity to work in a leading industry-geared research institute. The successful candidate will be located in Grenoble (France), in the foothills of the Alps, providing access to some of the best outdoors in the world (activities in this region include: snowboarding, skiing, golfing, hiking, kayaking, paragliding, rock climbing, fishing etc.). Please refer to the XRCE webpages (http://www.xrce.xerox.com) for further information regarding this position and on our research centre Applications should include the reference MLTT010208 and should be sent to following address: Mr. Christophe Mitenne Human Resources Xerox Research Centre Europe 6, chemin de Maupertuis 38240 MEYLAN, France ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Thu Feb 15 17:46:10 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Thu, 15 Feb 2001 18:46:10 +0100 Subject: Ecole: MASTER - UNIVERSITY OF CAMBRIDGE Message-ID: *** ONE YEAR GRADUATE COURSE *** ** STUDENTSHIPS AVAILABLE ** ------------------------------------------------------------------------ COMPUTER SPEECH, TEXT, AND INTERNET TECHNOLOGY ONE YEAR MASTERS COURSE THE DEPARTMENT OF ENGINEERING AND THE COMPUTER LABORATORY UNIVERSITY OF CAMBRIDGE ------------------------------------------------------------------------ This new Masters course replaces the highly successful M.Phil in Computer Speech and Language Processing. Like its predecessor, a key aim of the new Masters course in Computer Speech, Text and Internet Technology is to teach the fundamental theory of speech and natural language processing. However, the new course also focuses on its application to information management and access within the framework of emerging Internet and W3C standards, such as XML text and speech annotation and 3G wireless communication. It runs from early October to August and consists of two terms of lectures and practicals followed by a three month project. The final degree is awarded on the basis of coursework, examination and project. The course differs from some other programmes by providing an in-depth practical and theoretical grounding in the techniques for speech and language processing which form the basis for today's commercial and research prototype systems. There are strong links with industry and many of our past students have gone on to work for high-tech start-ups and industrial research laboratories, either immediately or after completing a PhD. To further strengthen our links with industry, we are making this course available to students wishing to pursue it on a part-time basis. Cambridge is a major international centre for research in both speech and language processing. The course is taught by leading researchers in these areas who have active collaborations with industrial and academic laboratories in Europe, the US and Japan. The EPSRC have funded a number of studentships for the course which are currently available to qualifying applicants. We especially encourage applications from students with a background in engineering, computer science, mathematics, linguistics and/or psychology. For further details please consult the course URL: http://svr-www.eng.cam.ac.uk/cstit/ or contact: Mrs Mavis Barber (Computer Speech, Text, and Internet Technology) Department of Engineering, University of Cambridge Trumpington Street, Cambridge CB2 1PZ, UK Tel: +44-1223-332752 Fax: +44-1223-332662 Email: mavis at eng.cam.ac.uk ------------------------------------------------------------------------ ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Thu Feb 15 17:46:25 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Thu, 15 Feb 2001 18:46:25 +0100 Subject: Appel: GL2001 Message-ID: =========================================================================== GL2001 GL2001 GL2001 GL2001 GL2001 GL2001 GL2001 GL2001 GL2001 GL2001 GL2001 1st International Workshop on Generative Approaches to the Lexicon =========================================================================== First call for participation April 26-28 2001 University of Geneva (Switzerland) http://issco-www.unige.ch/gl2001.html ---------------------------------------------------------------------------- - TOPIC The aim of this workshop is to bring together diverse contributions in philosophy, linguistics, computer science and lexicography to explore the lexicon from the point of view of generativity. The discussions will be centered, but are not limited to, the newly emerging view of Generative Lexicon Theory (Pustejovky, 1995). Topics include: - Philosophical Foundations of a Generative Approach - Representation of Word Meaning - Generative Lexicon Theory - Analysis of Linguistic Phenomena - Building Lexical Resources - Exploiting Lexical Resources in NLP Applications - Lexical Rules - Framework for Lexical Semantics - Critical Perspectives PROGRAM The program will include: - A SPECIAL TALK by James Pustejovsky (Brandeis University, Boston) - INVITED TALKS by Nicolletta Calzolari (Istituto Di Linguistica Computazionale, Pisa) Ann Copestake (Cambridge University, Cambridge) Hitoshi Isahara (Communications Research Laboratories, Kyoto) Evelyne Viegas (Microsoft, Natural Language Group, Redmond) Piek Vossen (Sail-labs, Antwerpen) Yorick Wilks (University of Sheffield, Sheffield) - 21 oral presentations (long (30 min) and short (20 min)) GL2001 is: - founded by the Swiss National Science Foundation (FNRS) and the Communications Research Laboratory (Kyoto) - hosted by University of Geneva, ISSCO/TIM. Organizers: Pierrette Bouillon (ISSCO/TIM, University of Geneva, Geneva) Kyoko Kanzaki (Communications Research Laboratory, Kyoto) The GL2001 program and registration form are now available at: http://issco-www.unige.ch/gl2001.html =========================================================================== GL2001 GL2001 GL2001 GL2001 GL2001 GL2001 GL2001 GL2001 GL2001 GL2001 GL2001 =========================================================================== ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Thu Feb 15 17:46:39 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Thu, 15 Feb 2001 18:46:39 +0100 Subject: Appel: DCAGRS_01 Message-ID: From: Bernd Reichel Dear Colleague, This is to inform you about the Third Workshop "Descriptional Complexity of Automata, Grammars and Related Structures" which will be held at the Technical University of Vienna (in conjunction with the Fifth International Conference on Developments in Language Theory). The goal of the workshop is to present the state of the art and to provide a forum for the exchange of new results. The Call for Papers and further information you can find at http://theo.cs.uni-magdeburg.de/dcagrs01/ Yours sincerely, Bernd Reichel ************************************************************************ Dr. Bernd Reichel Gebaeude 18 Raum 232 Fakult"at f"ur Informatik Tel.: +49-391-67-12851 Otto-von-Guericke-Universit"at Fax: +49-391-67-11250 Postfach 4120 reichel at iws.cs.uni-magdeburg.de 39016 Magdeburg http://theo.cs.uni-magdeburg.de/~reichel ************************************************************************ ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Thu Feb 15 17:46:59 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Thu, 15 Feb 2001 18:46:59 +0100 Subject: Appel: 4th INTEX Workshop Message-ID: French version below: 4th INTEX Workshop University of Bordeaux-3, June 11th and 12th juin, 2001 INTEX is a linguistic development environment that allows users to construct large-coverage linguistic resources, and to apply them to large texts. These resources can be DELA-type dictionaries, libraries of finite-state graphs and syntactic & semantic data bases in the form of lexicon-grammars. One characteristic of the system is that it is open: users can add their own linguistic resources and use elementary functionalities in their own applications, either by importing standalone programs, or by using the API. INTEX is used in more than 60 research centers as a linguistic tool, an information retrieval system, to teach second languages, as a terminological extractor, as well as to teach computational linguistics to graduate students. This fourth workshop will offer the INTEX users the opportunity to meet and share their experience in research, development and teaching. The latest additions to the features of INTEX will be presented. For the new INTEX users, or for researchers who use other linguistic development environments, the workshop will be an opportunity to discover a wide spectrum of projects that are based on the INTEX technology. Following the presentations, two tutorial sessions (initiation, advanced) will give participants an opportunity to play with the system. Submission process: By March 15th, 2001, submit a 1-page abstract to Claude Muller or Max Silberztein, using e-mail preferably. The title of the abstract should include: title of the paper, name, affiliation, postal address, e-mail address for each author. Authors will be notified of acceptance by April 15th. Contacts : Claude Muller UFR Lettres, Universit? de Bordeaux-3, Domaine Universitaire, 33607 PESSAC CEDEX (FRANCE). fax: +33(0)557 12 45 29 email: muller at montaigne.u-bordeaux.fr Max Silberztein IBM T.J. Watson Research Center 30 Sawmill River Road Hawthorne, NY 10532, USA fax: 1 (914) 784-6307 email: ms1 at us.ibm.com #-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#-#- 4?mes Journ?es INTEX Universit? de Bordeaux-3, les 11 et 12 juin 2001 INTEX est une plate-forme d'ing?nierie linguistique permettant de d?velopper des ressources linguistiques ? large couverture et de les appliquer ? des textes de taille importante. Ces ressources peuvent prendre la forme de dictionnaires ?lectroniques au format DELA, biblioth?ques de graphes ? ?tats finis et bases de donn?es syntactico-s?mantiques du type lexique-grammaire. L'une des particularit?s du syst?me est son ouverture : les utilisateurs peuvent ajouter leurs propres ressources et r?utiliser les fonctionnalit?s ?l?mentaires du syst?me dans leurs propres applications, soit ? partir de programmes individuels, soit ? partir de l'API. INTEX est utilis? dans plus de 60 centres de recherche universitaires ou priv?s comme outil de d?veloppement linguistique, moteur de recherche, aide ? l'enseignement des langues, outil d'extraction terminologique, et pour enseigner l'informatique linguistique. Comme les trois premi?res ?ditions (juin 1996, juin 1999, juin 2000), ces journ?es seront l'occasion pour les utilisateurs d'INTEX de se rencontrer et d'?changer leur exp?rience de d?veloppeur, de chercheur ou d'enseignant. Elles seront ?galement l'occasion de pr?senter les nouvelles fonctionnalit?s d'INTEX issues des r?cents d?veloppements. Pour les nouveaux utilisateurs ou les chercheurs travaillant avec d'autres syst?mes, ces journ?es offrent la possibilit? de d?couvrir un panel diversifi? de domaines d'application d'INTEX. En plus des communications portant sur des recherches ou d?veloppements en cours, deux tutoriels (initiation, avanc?) permettront d'exp?rimenter concr?tement le logiciel. Dates importantes: Veuillez envoyer un resume d'une page avant le 15 mars 2001 a Claude Muller ou Max Silberztein, par e-mail si possible. Le titre du resume doit contenir le titre de la presentation, la nom, l'affiliation, l'adresse postale et electronique de chaque auteur. Contacts : Claude Muller UFR Lettres, Universit? de Bordeaux-3, Domaine Universitaire, 33607 PESSAC CEDEX (FRANCE). fax: +33(0)557 12 45 29 email: muller at montaigne.u-bordeaux.fr Max Silberztein IBM T.J. Watson Research Center 30 Sawmill River Road Hawthorne, NY 10532, USA fax: 1 (914) 784-6307 email: ms1 at us.ibm.com ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Thu Feb 15 17:47:20 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Thu, 15 Feb 2001 18:47:20 +0100 Subject: Appel: EUROLAN 2001 WORKSHOP Message-ID: ******* EUROLAN 2001 WORKSHOP ******* MULTI-LAYER CORPUS-BASED ANALYSIS July 30 - August 1, 2001 Iasi, Romania http://www.cs.vassar.edu/~ide/Eurolan01-ws.html Organizers: Dan Cristea, University "A.I. Cuza", Iasi, Romania Nancy Ide, Vassar College, USA Daniel Marcu, ISI, University of Southern California Massimo Poesio, University of Edinburgh Corpora annotated for a variety of linguistic features are becoming increasingly available. Part of speech annotated corpora are commonplace; treebanks in a variety of languages are available or under development; and corpora annotated for various features of discourse, including co-reference and discourse structure, are also available (e.g., the MUC corpora). In addition, large speech corpora annotated with phonetic transcriptions and prosodic analysis and various multi-lingual aligned corpora are available from centers such as the Linguistic Data Consortium and the European Language Resources Association. This workshop will address issues of using corpora annotated for multiple layers (e.g., syntax and discourse, prosody and part of speech, etc.) or combining multiple layers of annotation in natural language analysis. We invite submissions on the following topics: o Research that exploits information on different linguistic levels; o Consideration and demonstration of the ways in which information from different layers can be used in automatic language processing; o Compatibility of corpora annotated for different linguistic layers, including means to harmonize different annotation types and levels; o Tools for exploiting different levels of annotation. The workshop will be held over three consecutive evenings in conjunction with the EUROLAN 2001 Summer School on Creation and Exploitation of Annotated Language Resources, in Iasi, Romania. Because EUROLAN 2001 is concerned with a wide variety of types of linguistic annotation, the workshop will serve to complement the content of lectures and tutorials that are part of the School's main program. Registration for the workshop is included in the Summer School registration fee. Information on EUROLAN 2001 is available at http://www.infoiasi.ro/~eurolan2001/ and http://www.clg.wlv.ac.uk/eurolan/ SUBMISSION INFORMATION: Papers should report on original work not previously presented elsewhere. The workshop is intended to provide a forum for discussion and a means to receive feedback for future development; therefore, papers describing both completed work and work-in-progress are acceptable. Submissions of 3500-5000 words should be sent via email to ide at cs.vassar.edu with the subject line "EUROLAN 2001 WORKSHOP SUBMISSION". Submissions in Postscript, PDF, or plain ASCII text formats are acceptable. DATES: Deadline for receipt of submissions : April 15, 2001 Notification of acceptance : May 1, 2001 Final Paper due : June 1, 2001 Workshop date : July 30 - August 1, 2001 PROGRAM COMMITTEE (tentative): Paul Buitelaar - DFKI, Saarbrucken Graeme Hirst - University of Toronto Eduard Hovy - University of Southern California Adam Kilgarriff - University of Brighton Ruslan Mitkov - University of Wolverhampton Sergei Nirenburg - New Mexico State University Laurent Romary - LORIA Nancy Dan Tufis - Romanian Academy Hans Uszkoreit - Saarland University of Saarbrucken Piek Vossen - Sail-labs, Antwerp-Berchem Yorick Wilks - University of Sheffield ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Thu Feb 15 17:48:43 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Thu, 15 Feb 2001 18:48:43 +0100 Subject: Publications: T.A.L. JOURNAL: SPECIAL ISSUE IN IR-ORIENTED NLP Message-ID: +-----------------------------------------------+ I T.A.L. journal I I (Le traitement automatique des langues) I I I I http://www.atala.org/tal/tal.html I +-----------------------------------------------+ SPECIAL ISSUE IN "INFORMATION RETRIEVAL-ORIENTED NATURAL LANGUAGE PROCESSING" Vol. 41, Num. 2, January 2001 -------------- Table of contents Christian JACQUEMIN : Pr?sentation du num?ro sur le traitement automatique des langues pour la recherche d'information Patrice BELLOT, Marc EL-B?ZE : Classification locale non supervis?e pour la recherche documentaire Pierrette BOUILLON, C?cile FABRE, Pascale S?BILLOT, Laurence JACQMIN : Apprentissage de ressources lexicales pour l'extension de requ?tes B?atrice DAILLE, Jean ROYAUT?, Xavier POLANCO : ?valuation d'une plate-forme d'indexation de termes complexes Georgette DAL, Fiammetta NAMER : G?n?ration et analyse automatiques de ressources lexicales construites utilisables en recherche d'informations Gael Harry DIAS, Sylvie GUILLOR?, Jean-Claude BASSANO, Jos? Gabriel PEREIRA LOPES : Extraction automatique d'unit?s lexicales complexes : Un enjeu fondamental pour la recherche documentaire ?ric GAUSSIER, Gregory GREFENSTETTE, David HULL, Claude ROUX : Recherche d'information en fran?ais et traitement automatique des langues Diego MOLLA, Rolf SCHWITTER, Michael HESS and Rachel FOURNIER : EXTRANS, An Answer Extraction System Fiammetta NAMER : FLEMM : Un analyseur flexionnel du fran?ais ? base de r?gles Martin RAJMAN, Romaric BESANCON, Jean-C?dric CHAPPELIER : Le mod?le DSIR: Une approche ? base de s?mantique distributionnelle pour la recherche documentaire -------------- All the members of the French Computational Linguistics Association ATALA receive the T.A.L. journal. To become a member of ATALA: http://www.atala.org/adhesion.html The issue can be ordered from Herm?s Sciences: hermes at iway.fr http://www.editions-hermes.fr/ ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Thu Feb 15 17:49:05 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Thu, 15 Feb 2001 18:49:05 +0100 Subject: Soft: ELRA News Message-ID: ___________________________________________________________ ELRA European Language Resources Association ELRA News ___________________________________________________________ *** ELRA NEW RESOURCES *** We are happy to announce new resources available via ELRA: - Telephone Speech Resources ELRA-S0094 Czech SpeechDat(E) Database ELRA-S0095 Slovak SpeechDat(E) Database ELRA-S0096 German SpeechDat(II) MDB-1000 Database - Written Corpus ELRA-W0026 PAROLE Irish Corpus A short description of each database is given below. Detailed information can be found on the following Website: http://www.elda.fr/catalog.html _______________________________________ TELEPHONE SPEECH RESOURCES _______________________________________ - ELRA-S0094 Czech SpeechDat(E) Database This database comprises 1052 Czech speakers (526 males, 526 females) recorded over the Czech fixed telephone network. - ELRA-S0095 Slovak SpeechDat(E) Database This database comprises 1000 Slovak speakers (498 males, 502 females) recorded over the Slovak fixed telephone network. - ELRA-S0096 German SpeechDat(II) MDB-1000 This database comprises 1295 German speakers (663 males, 610 females, 22 speakers with gender not specified) recorded over the German mobile telephone network. _______________________________________ WRITTEN CORPUS _______________________________________ ELRA-W0026 PAROLE Irish Corpus This corpus consists of over 8 million words The text is marked-up in accordance with the PAROLE encoding standard. All the files are in SGML format with a detailed header and the body of the text tagged to paragraph level. A subset of the corpus is morpho-syntactically tagged. Included in this distribution is approximately 3,000 manually checked words. ===================================== For further information, please contact: ELRA/ELDA Tel +33 01 43 13 33 33 55-57 rue Brillat-Savarin Fax +33 01 43 13 33 30 F-75013 Paris, France E-mail mapelli at elda.fr or visit our Web site: http//www.icp.grenet.fr/ELRA/home.html or http//www.elda.fr ===================================== ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Thu Feb 15 17:49:18 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Thu, 15 Feb 2001 18:49:18 +0100 Subject: Conf: IJCAI-01 Text Learning: Beyond Supervision (IJCAI workshop CFP) Message-ID: CALL FOR PAPERS IJCAI-01 Workshop on "Text Learning: Beyond Supervision" Monday, 6 August 2001 Seattle, Washington, USA www.cs.cmu.edu/~mccallum/textbeyond Submission deadline: March 23, 2001 Due to the rapidly increasing amount of textual data available and the range of interesting and important problems arising in text analysis, there has been growing interest in applying machine learning methods to text. There has also been significant recent interest in research that combines supervised and unsupervised learning. This research is especially relevant to text learning because the inherent complexity of natural language usually requires models with many parameters: estimating those parameters requires a lot of data, and obtaining labeled data is difficult and expensive. By combining unsupervised learning with supervised learning, the need for labeled training data can often be greatly reduced, allowing for the development of more powerful models and methods. The workshop will explore machine learning methods for solving supervised text learning tasks that exploit training methods beyond straightforward supervised learning. Relevant topics include: * Text classification with labeled and unlabeled data: EM, co-training, transduction with SVMs, discriminative maximum entropy with unlabeled data. * Information extraction with unlabeled data: bootstrapping, co-boosting. * Part-of-speech tagging, parsing and other NLP with unlabeled data. * Active learning: uncertainty sampling, query-by-committee, version space reduction. * Model selection with unlabeled data. * Word clustering for language modeling, distributional clustering, feature generation by clustering. * Semi-supervised clustering, document clustering with user-feedback. * Integrating prior knowledge into supervised learning, integrating distantly labeled data. * Unsupervised methods for learning segmentation models, translation models, lexicons, etc. * Link analysis for supervised learning. The goal of this workshop is to bring together researchers from the machine learning, information retrieval, computational linguistics and language modeling to talk about their different perspectives and to share their latest ideas. INVITED SPEAKERS ---------------- David Yarowsky Assistant Professor Department of Computer Science Johns Hopkins University http://www.cs.jhu.edu/~yarowsky/ Tommi Jaakkola Assistant Professor Department of Computer Science Massachusetts Institute of Technology http://www.ai.mit.edu/people/tommi/tommi.html SCHEDULE AND SUBMISSION PROCEDURE --------------------------------- Friday, Mar 23 2001 Paper submissions due Friday, Apr 06 2001 Acceptance notification Friday, Apr 20 2001 Camera ready papers due Authors are asked to prepare a paper in Postscript or PDF format. Submissions should conform to the IJCAI-2001 format, and be 8 pages or less. We encourage submissions containing original theoretical and applied concepts. Experimental results are also encouraged, even if they are only preliminary. To submit a paper, email it to textbeyond at whizbang.com before 6pm on the day of the deadline. ORGANIZING COMMITTEE -------------------- Andrew McCallum WhizBang Labs - Research, 4616 Henry Street, Pittsburgh, PA 15218 T: 412-683-9132 F: 412-683-4436 mccallum at whizbang.com http://www.cs.cmu.edu/~mccallum Kamal Nigam School of Computer Science, Carnegie Mellon, Pittsburgh, PA 15213 T: 412-268-3070 F: 412-268-5576 knigam at cs.cmu.edu http://www.cs.cmu.edu/~knigam Tony Jebara MIT, Media Laboratory - 20 Ames Street, E15-390, Cambridge, MA 02138 T: 617-253-0326 F: 617-253-8874 jebara at media.mit.edu http://www.media.mit.edu/~jebara Lillian Lee Department of Computer Science, Cornell University, Ithaca, NY 14853 T: 607-255-8119 F: 607-255-4428 llee at cs.cornell.edu http://www.cs.cornell.edu/home/llee ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Tue Feb 20 15:45:48 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Tue, 20 Feb 2001 16:45:48 +0100 Subject: Ecole: Training Workshop in Lexicography and Lexical Computing Message-ID: lexicom at itri A new Training Workshop in Lexicography and Lexical Computing http://www.itri.bton.ac.uk/lexicom The Information Technology Research Institute University of Brighton and The Lexicography MasterClass Brighton, England 16-20 July 2001 Trainers: Sue Atkins, Adam Kilgarriff, Michael Rundell Bringing together lexicographers linguists computer scientists to enable them to develop the skills needed for creating, managing and exploiting lexical data. building and working with text corpora dictionary/lexical databases writing lexical entries (for people and computers) All sessions will include practical work at a computer terminal. The workshop will be tailored to participants' interests; people will be encouraged to bring data from, and explore issues in current projects. For programme see http://www.itri.bton.ac.uk/lexicom/programme.html Location Brighton is a cosmopolitan city by the sea, one hour from London, 30 minutes from London's Gatwick Airport. A brochure and map will be sent to you on receipt of your registration. The workshop will take place on the University of Brighton's Moulsecoomb campus. The campus is 10 minutes by bus from Brighton Sea Front and city centre. There are inexpensive coffee bars and canteens on site. We shall use the IT Faculty Computer Suite which is equipped with over 100 modern PCs. Accommodation University accommodation has been reserved for registrants, in newly built units near the city centre, at a rate of GBP 27.50 per night (including breakfast). A booking form will be sent to you on receipt of your registration, or email conferences at brighton.ac.uk Related events The course will be the week after ACL/EACL in Toulouse, France, two weeks before CogSci in Edinburgh, Scotland, and two weeks after COMPLEX 2001 in Birmingham, England. Fees The registration fee for the course is GBP 600. Second and subsequent participants from the same institution are eligible for a 33% (GBP 200) discount. There is a late registration surcharge of GBP 100 for registrations received after 1st April 2001. Registrations now being accepted. For registration form, go to http://www.itri.bton.ac.uk/lexicom/reg_form.html Trainers: Sue Atkins was General Editor on the Collins-Robert English-French dictionaries and Lexicographic Consultant on the Oxford-Hachette. She is a Founder Member and Past President of Euralex, was the initiator of the British National Corpus and has co-developed the Frame Semantics paradigm with Charles Fillmore. Michael Rundell was Managing Editor of, amongst others the Longman Dictionary of Contemporary English (1987 and 1995 editions), the Longman Lanugage Activator, and the Bloomsbury/Macmillan Dictionary for Learners of English (forthcoming). He has lectured extensively on lexicography and language teaching. Atkins and Rundell have extensive experience of training many teams of lexicographers, for example for the newly-official African languages of South Africa. Adam Kilgarriff has published extensively on lexical computing and the interactions between lexicography and language engineering. He has been a consultant to Longman, Random House, Oxford University Press and Bloomsbury. He is currently President of ACL-SIGLEX. Supported by EURALEX, ELSNET and ACL SIGLEX European Association for Lexicography; European Language and Speech Network; Lexicons Special Interest Group of the Association for Computational Linguistics. http://www.itri.bton.ac.uk/lexicom ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Tue Feb 20 15:46:11 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Tue, 20 Feb 2001 16:46:11 +0100 Subject: Conf: Recital 01: extension de la date de soumission Message-ID: (see English version below) *********************************************************************** * * Recital 2001 * -------------------- * Rencontre des etudiants chercheurs en informatique * pour le traitement automatique * des langues * * Attention : extension de la date de soumission * au 6 MARS 2001 * * Universite de Tours * du lundi 2 au jeudi 5 juillet 2001 * * http://www.li.univ-tours.fr/taln-recital-2001/ * mailto:recital2001 at univ-tours.fr ********************************************************************** ********** Recital 2001 : DERNIER APPEL A COMMUNICATION ********** ----> DATE LIMITE DE SOUMISSION (Extension): MARDI 6 MARS 2001 <---- Recital 2001 aura lieu a Tours du lundi 2 au jeudi 5 juillet 2001 en parallele avec la conference TALN 2001 (appel a communications a paraitre separement). La conference Recital 2001 comprendra des communications scientifiques, des conferenciers invites, des seances de demonstration et posters, ainsi que des tutoriels. Les langues officielles de la conference sont le francais et l'anglais. Ces deux conferences sont organisees sous l'egide de l'ATALA (Association pour le Traitement Automatique des LAngues). ********** THEMES ********** Les communications pourront porter sur tous les themes habituels du TALN, incluant, de facon non limitative: Analyse et comprehension de textes Generation d'enonces en langues naturelles Traduction automatique Production de resumes Dialogue homme-machine Recital 2001 souhaite egalement accueillir des travaux de domaines proches dans lesquels le TALN joue un role important, dans la mesure ou l'accent est mis sur la composante TALN : Ressources linguistiques (lexiques, dictionnaires electroniques, corpus, etc.) Semantique lexicale (polysemie, categorisation, etc.) Semantique du temps et de l'espace (representation et raisonnement) Logique (argumentation, modelisation des intentions et des croyances, etc.) Architectures dediees au TAL (systE8mes multi-agents, reseaux neuromimetiques) Acquisition et apprentissage automatique de ressources ou de connaissances (a partir de corpus, ou de l'interaction humain/machine) Relations entre TAL et reconnaissance de la parole ********** CALENDRIER ********** ----> DATE LIMITE DE SOUMISSION : VENDREDI 23 FEVRIER 2001 <---- Notification aux auteurs : vendredi 27 avril 2001 Version finale (pret-a-clicher) : vendredi 11 mai 2001 Conference : du lundi 2 au jeudi 5 juillet 2001 ********** MODALITES DE SOUMISSION ********** Les articles soumis seront rediges en francais (ou en anglais par les non-francophones). Ils ne devront pas depasser 10 pages en Times 12, espacement simple, figures, exemples et references compris. Les soumissions devront parvenir au comite d'organisation avant le 23 fevrier 2001, sous forme electronique, a mailto:recital2001 at univ-tours.fr. En cas d'impossibilite d'envoi par courrier electronique, une soumission "papier" pourra etre admise. Dans ce cas, trois exemplaires devront etre envoyes a l'adresse suivante: Recital 2001 LI (Laboratoire d'Informatique de l'Universite de Tours) E3i, 64, avenue Jean Portalis 37200 Tours France ********** FORMAT DES SOUMISSIONS ********** Les auteurs devront envoyer leur soumission par courrier electronique sous la forme d'un document attache (fichiers ps ou pdf au format A4 et non Lettre US). Le message contiendra le titre de la soumission et les noms des auteurs. Les formats a utiliser pour la redaction sont disponibles sur le site de la conference: http://www.li.univ-tours.fr/taln-recital-2001. ********** CRITERES DE SELECTION ********** Les auteurs sont invites a soumettre des travaux de recherche originaux, n'ayant pas fait l'objet de publications anterieures. Les soumissions seront examinees par au moins deux specialistes du domaine. Seront considerees en particulier : l'importance et l'originalite de la contribution, la correction du contenu scientifique et technique, la discussion critique des resultats, en particulier par rapport aux autres travaux du domaine, la situation des travaux dans le contexte de la recherche internationale, l'organisation et la clarte de la presentation, l'adequation aux themes de la conference. Les articles selectionnes seront publies dans les actes de la conference. ********** POSTERS ********** Une ou deux seances specifiques seront prevues pour des posters (85 x 120 cm). Les propositions de poster suivent les memes regles que les soumissions de communication mais ne devront pas depasser 4 pages. ********** PRESENTATIONS ORALES ********** Les presentations orales dureront 15 minutes et seront suivies de 5 minutes de questions. Il sera possible d'utiliser un retro-projecteur ou un video-projecteur. ********** ACTES ********** Les actes des conferences seront distribues a tous les participants. **************************************************************** English version Submission deadline extended to 3/6/2001 **************************************************************** ********** Recital 2001 : LAST CALL FOR PAPERS ************ ----> SUBMISSION DEADLINE extended : Thursday, 3/06/2001 <---- Recital 2001 will be held in Tours, 2 - 5 July 2001, organized by the LI (Computer Laboratory of Tours University) and LTI (Language and Information Technologies). The official conference languages are French and English. The young researcher conference Recital 2001 will be held jointly with the conference TALN 2001. TALN 2001 is organized in collaboration with ATALA (Association pour le Traitement Automatique des LAngues). ********** TOPICS ********** Papers are invited in all areas of NLP, including (but not limited to): Analysis and comprehension of texts Text generation in natural languages Automatic translation Production of summaries Human Computer Interaction Recital 2001 also invites contributions in the following fields too: Linguistic resources (lexics, electronic dictionaries, corpora, etc.) Lexical Semantics (categorisation, etc.) Time and space Semantics (representation and reasoning) Logic (argumentation, modelisation of intention, etc.) NLP Dedicated architectures (multi-agents systems, neuromimetic networks) Acquisition and automatic learning of resources or knowledge (from corpora, or human/machine interaction) Relations between NLP and talk recognition ********** CALENDAR ********** ----> SUBMISSION DEADLINE: FRIDAY, 2/23/2001 <---- Notification to authors: 4/27/2001 Final version due (camera-ready): 5/11/2001 Conference : 7/2-5/2001 ********** SUBMISSION PROCEDURE ********** The maximum length for papers is 10 pages, in Times 12, single spaced, including figures, examples and references. Electronic submissions must reach the organizing committee before 2/23/2001, sent to mailto:recital2001 at univ-tours. If electronic submission is not possible, 3 hard copies of the paper must reach the organizing committee before 2/23/2001, at the following address: TALN 2001 LI (Laboratoire d'Informatique de l'Universite de Tours) E3i, 64, avenue Jean Portalis 37200 Tours France ********** FORMAT FOR SUBMISSIONS ********** Authors should send their submission as a file attached to an e-mail(ps or pdf files, A4 format and not US Letter format), containing the following information: submission title and author's names. The formats that MUST be used are available on the Conference website: http://www.li.univ-tours.fr/taln-recital-2001. ********** SELECTION CRITERIA ********** Authors are invited to submit original, previously unpublished work. Submissions will be reviewed by at least 2 specialists of the domain. Decisions will be based on the following criteria : Importance and originality of the paper Accuracy of the scientific and technical content Comparison of the results obtained with other relevant work Layout and clarity of the paper Relevance to the topics of the conference Accepted papers will be published in the proceedings of the conference. ********** POSTERS ********** One or two specific sessions for the posters (85 x 120 cm) will be scheduled in the conference. The poster submissions accord to the same rules of paper submission, BUT they should not exceed 4 pages. ********** TALKS ********** Papers should be of 15 minutes duration. 5 minutes will be left for questions. It will be possible to use a overhead projector or a video-projector. ********** COMITE DE PROGRAMME ********** ********** PROGRAM COMMITTEE ********** Pascal Amsili, TALaNa Pierre Beust, GREYC Philippe Blache, LPL Beatrice Bouchou, LI (president) Jean Caelen, CLIPS Cecile Fabre, ERSS Cedric Fairon, NYU, Department of Linguistics Bertrand Gaiffe, LORIA Damien Genthial, CLIPS Gabriel Illouz, LIMSI Denis Maurel, LI Philippe Muller, IRIT Anne Nicolle, GREYC Martin Rajman, EPFL Laurent Romary, LORIA Jose Rouillard, CLIPS Azim Roussanaly, LORIA Jacques Siroux, IRISA LLI/CORDIAL Jacques Vergne, GREYC Jean Veronis, LPL Michael Zock, LIMSI ********** COMITE D'ORGANISATION ********** ********** ORGANIZING COMMITTEE ********** Claire Agafonov, LTI Beatrice Bouchou, LI (president) Alain Cambourian, LTI Alain Delplanque, LTI Nathalie Friburger, LI (president) Nathalie Garric, LTI Paul Gaudin, LTI Manuel Gonzales de Avila, Ciremia Thierry Grass, LTI Denis Maurel, LI Nathalie Rossi, LTI Mohamed Slimane, LI Nicole Vincent, LI ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Tue Feb 20 15:46:28 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Tue, 20 Feb 2001 16:46:28 +0100 Subject: Appel: Fifth Workshop on Interlinguas Message-ID: Fifth Workshop on Interlinguas : Call for Papers The call for papers for the Fifth Workshop on Interlinguas is available at http://crl.nmsu.edu/Events/FWOI/FifthWorskhop/ The goal of this workshop is to bring together specialists to work out a practical, cross-language system of semantic relations for use in representing events and states of affairs including, but not limited to, participant relations (e.g., agent, patient, recipient, benefactee, instrument, etc.), spatial relations (e.g., anterior, posterior, superior, inferior, interior, etc.) and temporal relations (e.g., prior-to, following, concurrent, etc.). Papers are invited on: identifying systems of semantic relations and the linguistic devices for expressing them, methods for developing (or extending) such systems of relations, inferencing techniques for exploiting such systems of relations for particular MT tasks, such as disambiguation, reference resolution, the recovery of ellipted information, interpeting noun-noun compounds, metonymy and metaphor, etc. The workshop will be held on Wednesday, September 19, 2001, in conjunction with MT Summit VIII in Santiago de Compostela, Spain. Submission deadline: April 15, 2001 For further information, contact: Steve Helmreich or David Farwell shelmrei at crl.nmsu.edu david at crl.nmsu.edu 505.646.2141 505.646.5108 ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Tue Feb 20 15:46:47 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Tue, 20 Feb 2001 16:46:47 +0100 Subject: Soft: 2 annonces Message-ID: /1 Bigram Statistics Package (v0.3) /2 LANGUAGE INDEPENDENT PART-OF-SPEECH TAGGER -------------------------------------------------------------------------- /1 Bigram Statistics Package (v0.3) A newly improved version of the Bigram Statistics Package (v0.3) is now available! This is an easy to use suite of Perl tools for counting and analyzing bigrams in text. It includes a number of the standard tests of association, and also allows users to easily implement others without knowing very much about Perl at all. And it allows users to perform pairwise comparisons of the lists of bigrams found by these tests. This is free software. Get it (or more information) at: http://www.d.umn.edu/~tpederse/code.html Coming Soon - Unicode support! -- # Ted Pedersen http://www.d.umn.edu/~tpederse # # Department of Computer Science tpederse at d.umn.edu # # University of Minnesota Duluth # # Duluth, MN 55812 (218) 726-8770 # -------------------------------------------------------------------------- /2 LANGUAGE INDEPENDENT PART-OF-SPEECH TAGGER Dear Readers , Those interested in the two pieces of NLP software presented below are welcome to contact me directly ( gojol at sunu.rnc.ro ) . Thank you , Dr.ing. Vlad Gojol ---------------------------------- Senior Research Engineer Institutul National de Informatica Bucuresti , Romania ............................................................................ LANGUAGE INDEPENDENT PART-OF-SPEECH TAGGER I created a part-of-speech tagger with an unusual capacity of dealing with large contexts , especially for German . I used Negra ( seemingly the best known German corpus , with free obtainable licence ) . The tagger currently reputed as being the most accurate for German is perhaps TnT . It reports upon this corpus an error rate of 3.4% . But I have found a syste- matic error in Negra : all the occurences of the auxilliary verbs are tagged as auxilliary ( VAFIN ) , though in 50% of the cases they function as finite verbs ( VVFIN ) . I corrected a part of the corpus ( cca 40,000 tokens ) . In this more correct environment ( where the performance of TnT should be probably around 4.5% ) , my tagger gets 1.7% . On another German corpus ( I call it X ) , with comparable contents ( news- paper articles ) and tagset , but with attached EXTERIOR lexicon ( i.e. not extracted from the corpus ) , the result is 2.4% . I also used Susanne ( the only English corpus I could get free ) . The re- ported result for TnT is 3.8% . Mine is 2.8% . On the "A" texts , best paral- lelable with those in Negra , as journalistic , it's 2.3% . By restricting the tagset to a more normal size ( cca 100 tags , determined as optimal af- ter lots of test runs ) , it's 1.3% . Initially I had used a Romanian corpus , with a result of 0.9% ( compared to 1.7% , 2.5% and 4.2% respectively got by the Xerow , Birmingham and Brill taggers ) . The speed is comparable to that of TnT and modifiable by parameter setting , in reverse proportion to the accuracy ( but without affecting it much ) . The incremental operating mode and the data structures segmentation allow running on very small memory computers . There is the advantage of an intuitive output ( no hostile binary matrix ) , in a form analogue to the input of some expert systems . Alternative taggings are output , with scores : unlike with other taggers , they don't refer to individual words , but to whole sentence parts ( repre- senting somehow phrase surfaces of minimum energy ) . Special facilities exist , such as virtual tags , or context essentialisa- tion ( permitting to get the minimal contexts set characteristic to a certain linguisic style , useful not only for maximum accuracy and speed ) etc. Recently added features : wide-character support , the possibility of being called as a simple library routine , or suspending the notion of a file ( a complex files system is emulated into the memory ) . For example ( for the second feature above ) , you can create an instance of the tagger ( let's say for English with the tagset Lancaster ) , call it to tag a cer- tain text buffer ( by writing the resulting tags into another buffer ) and finally kill the instance , all this without using any disc file : t = GojolTagger_new("lancaster"); error_code = GojolTagger_tag(t,input_buffer,output_buffer); GojolTagger_free(t); All is built on two essentially new concepts : organicity and context pro- pagation . I didn't publish anything about them , to keep up their commercial appeal . The accuracy comparable to that of manual tagging made me find many errors in the used corpora : 98 in Negra , 36 in Susanne ; Prof. G. Sampson replied gratefully , saying that it's the first time somebody reports more than 2 errors , and that my findings make necessary a new version of Susanne . The handling of very large contexts could even modify the current tagsets de- sign , by cancelling some unnatural decisions ( motivated only by the incapa- city of the existing taggers to see beyond a 3-tokens neighborhood ) , such as those concerning the auxilliary verbs , participles etc. - so removing some burden from the subsequent stages of text processing . It is written in C ( Linux ) . Demos for German ( Negra ) and English ( Susanne ) are available . .............................................................................. LANGUAGE INDEPENDENT STATISTIC PARSER After learning from a 46,000 words pos-tagged corpus and a 32,000 words parsed ( treebank ) corpus , a 2,000 words text ( not included in any of the two corpora ) is parsed ( tagging excluded ) in 6 seconds ( on a 200 MHz machine ) with 2% incomplete trees ( but for these declared failures , are also provided well formed trees sufficient for a subse- quent translator ) - the extracted grammar having cca 12,000 rules . The Negra corpus of German was used . After learning from a 17,000 words parsed corpus and from the same 46,000 words pos-tagged one , a 2,000 words text included into the first ( but excluded from the second ) , to warrant that the grammar is complete relative to it ( i.e. contains all the rules necessary for its correct parsing ) , is processed in 2 seconds with no incomplete tree - the extracted grammar having cca 7,000 rules . The system is language independent - for English , upon the Susanne corpus , comparable results are obtained . To have an acceptable parser for any other i- diom , you need essentially simply a corpus with 30,000 tag- ged words , from which only 20,000 parsed as well - and for optimal results , 50,000 and 30,000 respectively . The parser may accept a set of rules intended to modify the statistical grammar deduced from the corpus . Moreover , it can take as input only a context-free grammar ( in which case it ceases to be a statistical parser ) , but in this operating mode it requires much time and memory ( during the learning , not during the parsing as such ) if the grammar is over-dimensioned . The statistical grammar is refined not by simply adding the proposed rules , but by modifying the corpus , to exploit all the real contexts possible for them . Semantic processing could be easily inserted at rule re- duction points . Actually this generalized parser can also work as a compiler generator : by appending specific semantic routines , you get efficient compilers for C , Pascal etc. This versatile system has more than 40 parameters which tune the accuracy and speed according to the target language sam- ple . The output is in treebank format and optionally in gra- phic ( with the trees effectively drawn ) one . Linux demos exist for German and English . As only the mi- nimal definition of C is used , it is easily adaptable to any machine ( for other Unix-like operating systems , probably a simple recompilation would be sufficient ) . ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Tue Feb 20 15:47:05 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Tue, 20 Feb 2001 16:47:05 +0100 Subject: Appel: ACL-2001 Workshop on Open-Domain Question Answering Message-ID: WORKSHOP ON OPEN-DOMAIN QUESTION ANSWERING ACL'2001 Conference Toulouse, France July 7, 2001 Open-domain question answering (QA) represents a new challenge to both commercial applications and academic research. When users have specific questions, such as "What countries did Clinton visit in 1999?" or "How much does a ThinkPad cost?", they would like to see one (or a few) succint answer(s). This workshop will focus on technical issues that directly apply to this challenge, in particular, theoretical and pragmatic issues involved in the creation, evaluation and implementation of QA techniques. We concentrate on QA that is automatic and either domain independent or working within a large open domain, such as news or technical support. To accommodate this need for automatically finding answers to open-domain questions, several different fields of research come together - information retrieval, natural-language processing and knowledge representation. This workshop will provide a forum for discussions of QA as the combination and integration of techniques from these three fields. We invite papers that deal with QA topics or components in one or more of these fields, such as answer identification using passage retrieval techniques, linguisitc analysis of questions to determine their focus, parse-based matching of questions and answers, text generation as used for formulating answers, deriving answers from knowledge bases, defining confidence measures for answers, etc. Other QA issues of interest are evaluation methods, user interface issues and user studies, integration of QA within larger systems, and commercial applications of QA. Topics of interest include, but are not limited to: - parsing of natural language used in analyzing questions and answers - semantic analysis and categorization of questions and answers - lexical resources and knowledge bases as used in QA - knowledge acquisition and information extraction used in QA - empirical methods for QA - methods for answer selection, synthesis and generation - definitions of answer correctness and answer justification - commercial applications for QA - integration of QA in dialog systems and search systems All papers should specifically focus on question answering. ORGANIZERS: Yael Ravin, T .J. Watson Research Center, IBM, USA John Prager, T .J. Watson Research Center, IBM, USA Sanda Harabagiu, Southern Methodits University, USA PROGRAM COMMITTEE: Jamie Callan, CMU Jaime Carbonell, CMU Donna Harman, NIST Graeme Hirst, Toronto Jerry Hobbs, SRI Christian Jacquemin, LIMSI Liz Liddy, Syracuse Marc Light, MITRE Dekang Lin, Alberta Steve Maiorano, AAT Dan Moldovan, SMU Dragomir Radev, Michigan Tomek Strzalkowski, SUNY Albany Ellen Voorhees, NIST SCHEDULE: Workshop paper submissions April 8, 2001 Notification of acceptance April 30, 2001 Deadline for camera-ready papers May 13, 2001 Workshop date July 7, 2001 SUBMISSION FORMAT AND INSTRUCTIONS: Submissions must be in English, no more than 8 pages long, and in the two-column format prescribed by ACL'2001. Please see http://acl2001.dfki.de/style/ for the detailed guidelines. Submissions should be sent electronically in either Word, pdf, or postscript format (only) no later than April 8, 2001 to: Yael Ravin ravin at us.ibm.com ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Tue Feb 20 15:47:23 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Tue, 20 Feb 2001 16:47:23 +0100 Subject: Appel: 2nd SIGdial Workshop on Discourse and Dialogue Message-ID: (We apologize if you receive this message more than once) 1st Announcement 2nd ACL SIGdial Workshop on Discourse and Dialogue Aalborg, Denmark, September 1-2 (Just before Eurospeech 2001-Scandinavia) More up to date information on submission schedule, formats, registration and program committee may be found at the workshop website Description Following up on the successful 1st Workshop in Hong Kong in October 2000, this will be the next in a series of workshops spanning the ACL SIGdial interest area of discourse and dialogue. While there has been a lot of activity in this area, and fairly frequent "specialty" workshops on various sub-topics, until this series there has not been a regular place for such research to be presented in a forum to receive attention from the larger SIGdial community and researchers outside this community. Invited Speakers: to be announced. Topics of Interest We welcome formal, corpus-based, implementational and analytical work on discourse and dialogue, with a focus on the following three themes: (i) Dialogue Systems Spoken, multi-modal, and text/web based dialogue systems including topics such as: * dialogue management models (specific subproblems or general modeling, in particular models for mixed initiative and user-adaptive dialogue); * speech, text, and graphics integration (for understanding or generation); * context-based interpretation and/or response planning,in particular how this contributes to natural interaction; * strategies for handling or preventing miscommuncation (repair and correction types, clarification and underspecificity, grounding and feedback strategies); * utilizing prosodic information for various types of disambiguation; * task-driven versus conversational dialogue; * evaluation of dialogue systems including task complexity measurements. (ii) Corpora and Corpus Tools Corpus-based work on discourse and spoken, text-based and multi-modal dialogue including its support, in particular: * issues and problems in discourse and dialogue annotation; * techniques (including machine learning), tools, coding schemes and data resources for discourse and dialogue studies; * XML-based tools for dialogue access to internet information. (iii) Pragmatic and/or Semantic Modeling The pragmatics and/or semantics of discourse and dialogue (i.e., beyond a single sentence) including the following issues: * the semantics/pragmatics of dialogue acts (including those which are less studied in the semantics/pragmatics framework); * incremental (plan-based,topic-based, etc.) models of discourse/dialogue structure integrating referential and relational structure; * modeling genre-specific aspects of discourse and dialogue structure, including the specific structural aspects of (interactive) digital media; * prosody in discourse and dialogue; * modeling politeness and non-recursive parts of discourse and dialogue; * models of presupposition and accommodation; * operational models of conversational implicature. Submission of Papers and Abstracts The program committee welcomes the submission of papers for full plenary presentation. The papers must be no longer than 10 pages, including title page, examples, references, etc. In addition to this, two additional pages are allowed as an appendix which may include extended example discourses or dialogues, algorithms, graphical representations, etc. Besides papers for full plenary presentation, we encourage the submission of short 4-page papers (inclusive title page, examples, references, etc.) to be combined with a short presentation in the plenary session and a poster presentation. Full papers and short papers should be sent electronically to the e-mail address sigdial2001 at ims.uni-stuttgart.de and must be received no later than May 7. The format to use for papers and abstracts is the same (ACL final paper format). Stylefiles are available at the workshop webpage: http://www.sigdial.org/sigdialworkshop01. Papers must be submitted in pdf (preferred) or postscript format. The title page should include the following information: Title: Authors' names, affiliations, and email addresses: Keywords (up to 5 keywords specifying subject area): Submission type (full paper or short paper submission): Abstract (short summary up to 5 lines): Important Dates Submission of full papers and short papers May 7 Notification June 20 Final submissions August 1 Workshop September 1-2 Workshop Publications Like full papers, short papers will be published in the workshop proceedings. Authors of a selected number of full papers accepted for the workshop proceedings will be asked to send in a version of their paper for the publication in a book on current directions and developments in discourse and dialogue, to be published by a renowned, international publisher. Panel Sessions In addition to the regular paper and abstract submissions, the program committee welcomes proposals for other relevant activities, such as reports of working groups and initiatives, and targeted discussion sessions. The program committee itself intends to organize two panel sessions, the descriptions of which will be given in later announcements, namely one specifically on spoken dialogue systems and the other on the pragmatics/semantics of discourse and dialogue being directly relevant to the first subject. Program Committee Co-Chairs: Jan van Kuppevelt (University of Stuttgart) and Ronnie Smith (East Carolina University) Organizing Committee Laila Dybkjaer (local chair), David Traum, Julia Hirschberg, Ronnie Smith, Jan van Kuppevelt. Contact Information: Questions about submission: Ronnie Smith/Jan van Kuppevelt Questions about local issues: Laila Dybkjaer Miscellaneous: David Traum ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Tue Feb 20 15:47:36 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Tue, 20 Feb 2001 16:47:36 +0100 Subject: Conf: TALN 2001 : extension de la date de soumission Message-ID: ********************************************************************** * * TALN 2001 * Traitement Automatique du Langage Naturel * * Universite de Tours * du lundi 2 au jeudi 5 juillet 2001 * * http://www.li.univ-tours.fr/taln-recital-2001/ * mailto::taln2001 at univ-tours.fr * ********************************************************************** (see English version below) ********** TALN 2001 : DERNIER APPEL A COMMUNICATION ********** ----> DATE LIMITE DE SOUMISSION (EXTENSION) : MARDI 6 MARS 2001 <---- TALN 2001 aura lieu a Tours du lundi 2 au jeudi 5 juillet 2001, organise par le LI (Laboratoire d'Informatique de l'Universit? de Tours) et l'axe LTI (Langues et Technologies de l'information). La conference TALN 2001 comprendra des communications scientifiques, des conferenciers invites, des seances de demonstration et posters, ainsi que des tutoriels. Les langues officielles de la conference sont le francais et l'anglais. TALN 2001 est organisee sous l'egide de l'ATALA (Association pour le Traitement Automatique des LAngues) et se tiendra conjointement a la conference pour jeunes chercheurs RECITAL 2001 (appel a communications a paraitre separement). ********** THEMES ********** Les communications pourront porter sur tous les themes habituels du TALN, incluant, de facon non limitative: lexique morphologie syntaxe semantique pragmatique discours analyse generation resume dialogue traduction automatique approches logiques, symboliques et statistiques TALN 2001 souhaite egalement accueillir des travaux de domaines proches dans lesquels le TALN joue un role important, dans la mesure ou l'accent est mis sur la composante TALN : traitement de la parole (prosodie, linguistique, pragmatique) traitement de l'ecrit aspects cognitifs terminologie acquisition de connaissances a partir de textes extraction d'information recherche documentaire linguistique de corpus linguistique mathematique utilisation d'outils de TALN pour la modelisation linguistique enseignement assiste, enseignement des langues. Sont aussi attendus des travaux sur des applications du TALN, implementees et evaluees, faisant ressortir leurs aspects scientifiques et les enseignements tires. Des demonstrations de systemes pourront etre proposees, independamment ou en complement d'articles scientifiques. L'emploi du temps de la conference comprendra une session pour ces demonstrations. ********** CALENDRIER ********** ----> DATE LIMITE DE SOUMISSION (EXTENSION) : MARDI 6 MARS 2001 <---- Notification aux auteurs : vendredi 27 avril 2001 Version finale (pret-a-clicher) : vendredi 11 mai 2001 Conference : du lundi 2 au jeudi 5 juillet 2001 ********** MODALITES DE SOUMISSION ********** Les articles soumis seront rediges en francais (ou en anglais par les non-francophones). Ils ne devront pas depasser 10 pages en Times 12, espacement simple, figures, exemples et references compris. Les soumissions devront parvenir au comite d'organisation avant le 6 mars 2001, sous forme electronique, a mailto:taln2001 at univ-tours.fr. En cas d'impossibilite d'envoi par courrier electronique, une soumission "papier" pourra etre admise. Dans ce cas, trois exemplaires devront etre envoyes a l'adresse suivante: TALN 2001 LI (Laboratoire d'Informatique de l'Universite de Tours) E3i, 64, avenue Jean Portalis 37200 Tours France ********** FORMAT DES SOUMISSIONS ********** Les auteurs devront envoyer leur soumission par courrier electronique sous la forme d'un document attache (fichiers ps ou pdf au format A4 et non Lettre US). Le message contiendra le titre de la soumission et les noms des auteurs. Les formats a utiliser pour la redaction sont disponibles sur le site de la conference: http://www.li.univ-tours.fr/taln-recital-2001. ********** CRITERES DE SELECTION ********** Les auteurs sont invites a soumettre des travaux de recherche originaux, n'ayant pas fait l'objet de publications anterieures. Les soumissions seront examinees par au moins deux specialistes du domaine. Seront considerees en particulier : L'importance et l'originalite de la contribution, La correction du contenu scientifique et technique, La discussion critique des resultats, en particulier par rapport aux autres travaux du domaine, La situation des travaux dans le contexte de la recherche internationale, L'organisation et la clarte de la presentation, L'adequation aux themes de la conference. Les articles selectionnes seront publies dans les actes de la conference. ********** DEMONSTRATIONS ET POSTERS ********** Une ou deux seances specifiques seront prevues pour des demonstrations (presentations logicielles) et des posters (85 x 120 cm). Les propositions de demonstration ou de poster suivent les memes regles que les soumissions de communication mais ne devront pas depasser 4 pages. ********** PRESENTATIONS ORALES ********** Les presentations orales dureront 20 minutes et seront suivies de 10 minutes de questions. Il sera possible d'utiliser un retro-projecteur ou un video-projecteur. ********** ACTES ********** Les actes de la conference seront distribues a tous les participants. Le Comite de redaction de la revue Traitement Automatique des Langues (t.a.l.) s?lectionnera deux articles pour publication. ********************************************************************** * * ENGLISH VERSION * ********************************************************************** ********** TALN 2001 : FINAL CALL FOR PAPERS ********** ----> EXTENDED SUBMISSION DEADLINE: TUESDAY, 3/6/2001 <---- TALN 2001 will be held at Tours on July, 2 - 5 2001, organized by the LI (Computer Laboratory of Tours University) and LTI (Language and Information Technologies). The conference includes paper presentations, invited speakers, tutorials and software demonstrations. The official conference languages are French and English. TALN 2001 is organized in collaboration with ATALA (Association pour le Traitement Automatique des LAngues) and will be held jointly with the young researcher conference RECITAL 2001 (a separate call for papers will follow). ********** TOPICS ********** Papers are invited in all areas of NLP, including (but not limited to): lexicon morphology syntax semantics pragmatics discourse parsing generation abstraction/summarisation dialogue translation logical, symbolical and statistical approaches TALN 2001 also invites contributions in fields for which NLP plays an important role, as long as these contributions emphasize their NLP dimension : speech processing text processing cognition terminology knowledge acquisition information retrieval documentary research corpus-based linguistics mathematical linguistics management and acquisition of linguistic resources computer assisted learning NLP tools for linguistic modelization TALN 2001 also welcomes submissions focusing on NLP applications that have been implemented, tested and evaluated and emphasizing the scientific aspects and conclusions drawn. Software demonstrations can be proposed, either independently or in connection with a paper proposal. Specific sessions for the demos will be scheduled in the conference. ********** CALENDAR ********** ----> EXTENDED SUBMISSION DEADLINE: TUESDAY, 3/6/2001 <---- Notification to authors: 4/27/2001 Final version due (camera-ready): 5/11/2001 Conference : 7/2-5/2001 ********** SUBMISSION PROCEDURE ********** The maximum length for papers is 10 pages, in Times 12, single spaced, including figures, examples and references. Electronic submissions must reach the organizing committee before 3/6/2001, sent to mailto:taln2001 at univ-tours.fr. If electronic submission is not possible, 3 hard-copies of the paper must reach the organizing committee before 3/6/2001, at the following address: TALN 2001 LI (Laboratoire d'Informatique de l'Universite de Tours) E3i, 64, avenue Jean Portalis 37200 Tours France ********** FORMAT FOR SUBMISSIONS ********** Authors should send their submission as a file attached to an e-mail(ps or pdf files, A4 format and not US Letter format), containing the following informations: submission title and author's names. The formats that MUST be used are available on the Conference web site: http://www.li.univ-tours.fr/taln-recital-2001/ . ********** SELECTION CRITERIA ********** Authors are invited to submit original, previously unpublished work. Submissions will be reviewed by at least 2 specialists of the domain. Decisions will be based on the following criteria : Importance and originality of the paper Accuracy of the scientific and technical content Comparison of the results obtained with other relevant work Layout and clarity of the paper Relevance to the topics of the conference Accepted papers will be published in the proceedings of the conference. ********** DEMOS AND POSTERS ********** One or two specific sessions for the demos and the posters (85 x 120 cm) will be scheduled in the conference. The demo or poster submissions accord to the same rules of paper submission, BUT they should not exceed 4 pages. ********** TALKS ********** Papers should be of 20 minutes duration. 10 minutes will be left for questions. It will be possible to use a overhead projector or a video-projector. ********** PROCEEDINGS ********** The conference proceedings will be given to all participants. The editorial staff of the journal Traitement Automatique des Langues (t.a.l.) will select two papers for publication. ********** COMITE DE PROGRAMME ********** ********** PROGRAMME COMMITTEE ********** (le comite de programme sera entoure d'un large comite de lecture) (the program committee will be supervised by a broad reviewing committee) Pascal Amsili, TALaNa Frederic Bechet, LIA Philippe Blache, LPL Christian Boitet, CLIPS-GETA Pierrette Bouillon, ISSCO Beatrice Daille, IRIN Laurence Danlos, LORIA/TALaNa Claire Gardent, LORIA Eric Laporte, CERIL Denis Maurel, LI (president) Piet Mertens, CCL Jean-Marie Pierrel, LORIA Martin Rajman, EPFL Owen Rambow, ATT Labs-Research Jacques Siroux, IRISA LLI/CORDIAL Jean Veronis, LPL Pierre Zweigenbaum, DIAM ********** COMITE D'ORGANISATION ********** ********** ORGANIZING COMMITTEE ********** Claire Agafonov, LTI Beatrice Bouchou, LI Alain Cambourian, LTI Alain Delplanque, LTI Nathalie Friburger, LI Nathalie Garric, LTI Paul Gaudin, LTI Manuel Gonzales de Avila, Ciremia Thierry Grass, LTI Denis Maurel, LI (president) Nathalie Rossi, LTI Mohamed Slimane, LI Nicole Vincent, LI ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Tue Feb 20 15:48:07 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Tue, 20 Feb 2001 16:48:07 +0100 Subject: Appel: BUlletin de Linguistique Appliquée et Générale Message-ID: CALL FOR PAPERS The theme for the next number of BULAG (BUlletin de Linguistique Appliqu?e et G?n?rale) Theme: Internet and Natural Language Processing Coordonated by: Henri MADEC Papers to be sent to: Henri MADEC Centre de Recherche en Linguistique Lucien Tesni?re Facult? des Lettres 30, rue M?gevand 25030 Besan?on cedex France henri.madec at univ-fcomte.fr Submission deadline: 04/30/2000 Information concerning the papers format : Papers should be in the region of 10 pages. Each paper should have the following form. Chaque article devra ?tre ?dit? sous la forme suivante : Title Author Name of research Centre University City Country R?sum? en fran?ais Key-words Abstract in English Key-words Paper References You can download a word 95/97 format model from the following address: http://tesniere.univ-fcomte.fr/ressourc/blgmoden.doc You can download an RTF format model from the following adress: http://tesniere.univ-fcomte.fr/ressourc/blgmoden.rtf Document format: Upper margin Lower margin Left margin Right margin Headers Footers Height x Width Font sizes: principal title 14, other title 10, text 10 Interparagraph spacing Space between paragraph title and paragraph 2,5 cm. 2,5 cm. 2 cm. 2 cm. 1,25 cm. 1,25 cm. 21 cm. x 14,8 cm. 6 pts. 3 pts. File formats Word 95, Word 97, RTF, Fonts Times New Roman (if you use other fonts please supply these with your paper) Submission: by E-Mail (attached file) to: henri.madec at univ-fcomte.fr or by post, in a 1.44 MB diskette, PC format, to Henri MADEC Centre de Recherche en Linguistique Lucien Tesni?re Facult? des Lettres 30, rue M?gevand 25030 Besan?on cedex France ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Tue Feb 20 15:48:17 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Tue, 20 Feb 2001 16:48:17 +0100 Subject: Appel: NAACL2001 3 workshops Message-ID: NAACL 2001 Workshop on 1/ WordNet and Other Lexical Resources: 2/ Workshop on Automatic Summarization 2001 3/ Adaptation in Dialogue Systems ------------------------------------------------------------------- 1/ WordNet and Other Lexical Resources: Applications, Extensions and Customizations http://www.seas.smu.edu/~moldovan/mwnw/ NAACL 2001 Workshop Carnegie Mellon University, Pittsburgh 3 and 4 June, 2001 Sponsored by the Association for Computational Linguistics Special Interest Group on the Lexicon. Previously announced as two different workshops: - WordNet: Extensions and NLP Applications - Customizing Lexical Resources Lexical resources have become important basic tools within NLP and related fields. The range of resources available to the researcher is diverse and vast - from simple word lists to complex MRDs and thesauruses. The resources contain a whole range of different types of explicit linguistic information presented in different formats and at various levels of granularity. Also, much information is left implicit in the description, e.g. the definition of lexical entries generally contains genus, encyclopaedic and usage information. The majority of resources used by NLP researchers were not intended for computational uses. For instance, MRDs are a by-product of the dictionary publishing industry, and WordNet was an experiment in modelling the mental lexicon. In particular, WordNet has become a valuable resource in the human language technology and artificial intelligence. Due to its vast coverage of English words, WordNet provides with general lexico-semantic information on which open-domain text processing is based. Furthermore, the development of WordNets in several other languages extends this capability to trans-lingual applications, enabling text mining across languages. For example, in Europe, WordNet has been used as the starting point for the development of a multilingual database for several European languages (the EuroWordNet project). Other resources such as the Longman Dictionary of Contemporary English and Roget's Thesaurus have also been used for various NLP tasks. The topic of this workshop is the exploitation of existing resources for particular computational tasks such as Word Sense Disambiguation, Generation, Information Retrieval, Information Extraction, Question Answering and Summarization. We invite paper submissions that include but are not limited to the following topics: - Resource usage in NLP and AI - Resource extension in order to reflect the lexical coverage within a particular domain; - Resource augmentation by e.g. adding extra word senses, enriching the information associated with the existing entries. For instance, recently, several extensions of the WordNet lexical database have been initiated, in the United States and abroad, with the goal of providing the NLP community with additional knowledge that models pragmatic information not always present in the texts but required by document processing; - Improvement of the consistency or quality of resources by e.g. homogenizing lexical descriptions, making implicit lexical knowledge explicit and clustering word senses; - Merging resources, i.e. combining the information in more than one resource e.g. by producing a mapping between their senses. For instance, WordNet has been incorporated in several other linguistic and general knowledge bases (e.g. FrameNet and CYC); - Corpus-based acquisition of knowledge; - Mining common sense knowledge from resources; - Multilingual WordNets and applications; Paper submission Submissions must use the NAACL latex style or Microsoft Word style (see workshop website). Paper submissions should consist of a full paper (6 pages or less). Submission procedure Electronic submission only. For U.S. papers please send the pdf or postscript file of your paper to: moldovan at seas.smu.edu. Please submit papers from other countries to w.peters at dcs.shef.ac.uk. Because review is blind, no author information is included as part of the paper. A separate identification page must be sent by email including title, all authors, theme area, keywords, word count, and an abstract of no more than 5 lines. Late submissions will not be accepted. Notification of receipt will be e-mailed to the first author shortly after receipt. Please address any questions to moldovan at seas.smu.edu or w.peters at dcs.shef.ac.uk Important dates Paper submission deadline: February 20, 2001 Notification of acceptance: March 10, 2001 Camera ready due: March 25, 2001 Workshop date: June 3 and 4, 2001 Organizers Sanda Harabagiu, SMU, sanda at seas.smu.edu Dan Moldovan, SMU, moldovan at seas.smu.edu Wim Peters, University of Sheffield, wim at dcs.shef.ac.uk Mark Stevenson, University of Sheffield, marks at dcs.shef.ac.uk Yorick Wilks, University of Sheffield, yorick at dcs.shef.ac.uk Programme Committee Roberto Basili (Universita di Roma Tor Vergata) Martin Chodorow (Hunter College of CUNY) Christiane Fellbaum (Princeton University) Ken Haase (MIT) Sanda Harabagiu (SMU) Graeme Hirst (University of Toronto) Robert Krovetz, NEC Claudia Leacock (ETS) Steven Maiorano (AAT) Rada Mihalcea (SMU) Dan Moldovan (SMU) Simonetta Montemagni (Istituto di Linguistica Computazionale, Pisa) Martha Palmer (University of Pennsylvania) Maria Tereza Pazienza (Universita di Roma Tor Vergata) Wim Peters (University of Sheffield) German Rigau (Universitat Politecnica de Catalunya) Mark Stevenson (University of Sheffield) Randee Tengi (Princeton University) Paola Velardi (University of Roma "La Sapienza") Ellen Voorhees (NIST) Piek Vossen (Sail Labs) Yorick Wilks (University of Sheffield) --------------------------------------------------------------------- 2/ Workshop on Automatic Summarization 2001 (pre-conference workshop in conjunction with NAACL2001) Sunday, June 3, 2001 Pittsburgh, Pennsylvania, USA sponsored by ACL (Association for Computational Linguistics) MITRE Corporation New submission deadline: Febuary 23, 2001 Organizing Committee: Jade Goldstein Carnegie Mellon University jade+ at cs.cmu.edu Chin-Yew Lin USC/Information Sciences Institute cyl at isi.edu Program Committee: Breck Baldwin Baldwin Language Tech Hsin-Hsi Chen National Taiwan University Udo Hahn Universitaet Freiburg Eduard Hovy USC/Information Sciences Institute Hongyan Jing Columbia University Elizabeth Liddy Syracuse University Daniel Marcu USC/Information Sciences Institute Inderjeet Mani MITRE Shigeru Masuyama Toyohashi University of Technology Marie-Francine Moens Katholieke Universiteit Leuven Vibhu Mittal Google Research Sung Hyon Myaeng Chungnam National University Akitoshi Okumura NEC Chris Paice Lancaster University Dragomir Radev University of Michigan, Ann Arbor Karen Sparck-Jones University of Cambridge Tomek Strzalkowski State University of New York, Albany Simone Teufel Columbia University Workshop Website: http://www.isi.edu/~cyl/was-naacl2001 (for the latest update) I. OVERVIEW II. CALL FOR PAPERS III. FORMAT FOR SUBMISSION I. OVERVIEW The problem of automatic summarization poses a variety of tough challenges in both NL understanding and generation. A spate of recent papers and tutorials on this subject at conferences such as ACL, ANLP/NAACL, ACL/EACL, AAAI, ECAI, IJCAI, and SIGIR point to a growing interest in research in this field. Several commercial summarization products have also appeared. There have been several workshops in the past on this subject: Dagstuhl in 94, ACL/EACL in 97, the AAAI Spring Symposium in 98, and ANLP/NAACL in 2000. All of these were extremely successful, and the field is now enjoying a period of revival and is advancing at a much quicker pace than before. NAACL'2001 is an ideal occasion to host another workshop on this problem. II. CALL FOR PAPERS The Workshop on Automatic Summarization program committee invites papers addressing (but not limited to): Summarization Methods: use of linguistic representations, statistical models, NL generation for summarization, production of abstracts and extracts, multi-document summarization, narrative techniques in summarization, multilingual summarization, text compaction, multimodal summarization (including summarization of audio), use of information extraction, studies and modeling of human summarizers, improving summary coherence, concept fusion, use of thesauri and ontologies, trainable summarizers, applications of machine learning, knowledge-rich methods. Summarization Resources: development of corpora for training and evaluating summarizers, annotation standards, shared summarization tools, document segmentation, topic detection, and clustering related to summarization. Evaluation Methods: intrinsic and extrinsic measures, on-line and off-line evaluations, standards for evaluation, task-based evaluation scenarios, user studies, inter-judge agreement. Workshop Themes: 1. Summarization Applications 2. Multidocument Summarization 3. Multilingual Text Summarization 4. Evaluation and Text/Training Corpora 5. Generation for Summarization 6. Topic Identification for Summarization 7. Integration with Web and IR Access III. FORMAT FOR SUBMISSION Submissions must use the ACL latex style or Microsoft Word style WAS-submission.doc (both available from the Automatic Summarization workshop web page). Paper submissions should consist of a full paper (5000 words or less, including references). SUBMISSION QUESTIONS Please send submission questions to cyl at isi.edu SUBMISSION PROCEDURE Electronic submission only: send the pdf (preferred), postscript, or MS Word form of your submission to: cyl at isi.edu. The Subject line should be "NAACL2001 WORKSHOP PAPER SUBMISSION". Because reviewing is blind, no author information is included as part of the paper. An identification page must be sent in a separate email with the subject line: "NAACL2001 WORKSHOP ID PAGE" and must include title, all authors, theme area, keywords, word count, and an abstract of no more than 5 lines. Late submissions will not be accepted. Notification of receipt will be e-mailed to the first author shortly after receipt. DEADLINES Paper submission deadline: Feburary 23, 2001 Notification of acceptance for papers: March 23, 2001 Camera ready papers due: April 6, 2001 Workshop date: June 3, 2001 --------------------------------------------------------------------- 3/ NAACL 2001 Workshop on Adaptation in Dialogue Systems Webpage: www.cs.utah.edu/~cindi/AdaptDial.html Overview The purpose of this workshop is to bring together researchers investigating the application of learning and adaptation to dialogue systems, both speech and text based. Methods for learning and adaptation show promise for enhancing the robustness, flexibility, and overall accuracy of dialogue systems. While researchers in many parts of computational linguistics who use these methods have begun to form communities, the burgeoning set of activities within dialogue has remained relatively disparate. We are interested in adaptation that includes learning procedures as well as decision making methods aimed at dynamically reconfiguring dialogue behavior based on the context. We would also like to explore techniques that allow a dialogue system to learn with experience or from data sets gathered from empirical studies. Researchers looking at methods to automatically improve different modules of dialogue systems, or the system as a whole, have not had many opportunities to come together to share their work. We thus welcome submissions from researchers supplementing the traditional development of dialogue systems with techniques from machine learning, statistical NLP, and decision theory. Call For Papers We solicit papers from a number of research areas, including: - Use of machine learning techniques at all levels of dialogue, from speech recognition to generation; from dialogue strategy to user modeling - Adapting to the user as a dialogue progresses - Dialogue as decision making under uncertainty - User and user group modeling - Use of corpora in developing components of dialogue systems, including issues in annotation - Evaluation of adaptive dialogue systems - Comparison of different techniques in applying adaptive techniques to dialogue We also hope to include a session for the demonstration of working systems, as time permits. The demonstration sessions will be open to anyone who wishes to bring their adaptive conversational systems for demonstration to other members of the workshop. Presenters are asked to submit a paper that is specifically directed at a demonstration of their current systems. Important Dates (2001): Paper submission deadline: Feb 19 Notification of acceptance for papers: Mar 16 Camera ready papers due: Mar 30 Workshop date: Jun 4 Paper Submission Electronic submission only: send the postscript or pdf form of your submission to: timpaek at microsoft.com. The Subject line should be "NAACL2001 WORKSHOP PAPER SUBMISSION". A cover page should be included with title, all authors, theme area, keywords, word count, and an abstract of no more than 5 lines. Late submissions will not be accepted. Notification of receipt will be e-mailed to the first author shortly after receipt. Please address any questions to timpaek at microsoft.com Submissions must use the NAACL latex style or Microsoft Word style. Paper submissions should consist of a full paper (6 pages or less). The templates are available at the workshop web site. Organizers Eric Horvitz Microsoft Research horvitz at microsoft.com Tim Paek Microsoft Research timpaek at microsoft.com Cindi Thompson University of Utah cindi at cs.utah.edu Program Committee Jennifer Chu-Carroll IBM Peter Heeman Oregon Graduate Institute Diane Litman AT & T Labs Candace Sidner MERL Marilyn Walker AT & T Labs ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Tue Feb 20 15:51:02 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Tue, 20 Feb 2001 16:51:02 +0100 Subject: Appel: SEMPRO-2001 Message-ID: COGNITIVELY PLAUSIBLE MODELS OF SEMANTIC PROCESSING SEMPRO-2001 (A workshop in conjunction with the Annual Meeting of the Cognitive Science Society) July 31st, Edinburgh University http://www.hcrc.ed.ac.uk/~sempro/ The goal of this workshop is to provide a forum to present models of semantic processing (computational and non-computational) motivated by psychological evidence or corpus studies. Topics of interest include: - incrementality and underspecification in semantic processing - lexical access and disambiguation - semantic composition (e.g., interpretation of modifiers such as adjectives, of modal expressions, of negation) - anaphora resolution - scope assignment - detection and exploitation of discourse structure - semantic interpretation in dialogues (e.g., models of grounding) We would especially like to encourage the exchange of results between psychological experimentation, computational modelling, and corpus-based work. PROGRAM COMMITTEE (tentative): Massimo Poesio, Alan Garnham, Maria Lapata, Julie Sedivy, Rosemary Stevenson, Peter Wiemer-Hastings SUBMISSION PROCEDURE: Anonymous extended abstracts of at most 5 pages should be submitted by e-mail to sempro at cogsci.ed.ac.uk. Include the words 'Submission for SEMPRO 2001' in the Subject line. Accepted formats: ASCII, postscript, pdf. DATES: Papers due: April 15th Acceptance Notification: June 15th. ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Tue Feb 20 15:53:26 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Tue, 20 Feb 2001 16:53:26 +0100 Subject: Appel: CoNLL-2001 Message-ID: APOLOGIES FROM MULTIPLE SUBMISSIONS CALL FOR PAPERS CoNLL-2001 Fifth Computational Natural Language Learning Workshop Toulouse, France, July 6-7, 2001 http://lcg-www.uia.ac.be/conll2001/ BACKGROUND CoNLL is the yearly workshop organized by SIGNLL, the Association for Computational Linguistics Special Interest Group on Natural Language Learning (http://www.aclweb.org/signll/). Previous CoNLL meetings were held in Madrid (1997), Sydney (1998), Bergen (1999) and Lisbon (2000). The 2001 event will be held as a two-days workshop at the 39th Annual Meeting of the Association for Computational Linguistics (ACL), July 6-11, 2001 in Toulouse, France. This year, a special theme will be the focus of the workshop: Interaction and Automation in Language Learning Resources Apart from this special theme, the workshop will accept contributions about language learning topics, including, but not limited to: - Computational models of human language acquisition - Computational models of the origins and evolution of language - Machine learning methods applied to natural language processing tasks (speech processing, phonology, morphology, syntax, semantics, discourse processing, language engineering applications) - Symbolic learning methods (Rule Induction and Decision Tree Learning, Lazy Learning, Inductive Logic Programming, Analytical Learning, Transformation-based Error-driven Learning) - Biologically-inspired methods (Neural Networks, Evolutionary Computing) - Statistical methods (Bayesian Learning, HMM, maximum entropy, SNoW, Support Vector Machines) - Reinforcement Learning - Active learning, ensemble methods, meta-learning - Computational Learning Theory analyses of language learning - Empirical and theoretical comparisons of language learning methods - Models of induction and analogy in Linguistics This year's workshop will also accept submissions for a shared task (segmenting a text into clauses-clausing). THE WORKSHOP Main Session Theme: Interaction and Automation in Language Learning Resources The purpose of the special theme is to present and discuss state-of-the-art learning mechanisms for the automated acquisition of language resources (dictionaries, ontologies, grammars) or the automated adaptation of natural language resources/processors to new domains or languages. The dimensions of learning that are of interest for this session include: - The integration of humans/linguists in the learning process - The structure of the training data - The kind of knowledge that is learned - General study of learning methods that are suitable for natural language related tasks Lately there have been new learning mechanisms that use either large amounts of raw data or small sets of carefully constructed tagged training samples. Learning language can be construed as learning numbers or parameters for some statistical or symbolic system, or learning rules assigning structures to input data (or a mix of those). Learning can be done off-line, which introduces the problem of interpreting (if needed) the derived knowledge before its use in an NLP engine; or on-line, which raises user interaction problems. Different approaches are tailored to solve different kinds of problems subject to a different balance of requirements (large vs. small training set, tagged vs. untagged training data, results needs interpretation or can be used as is, etc.). While this session aims at presenting the largest panorama of learning techniques, we encourage submission of work on semi-automated learning techniques that involve interaction with a human during the learning process or the intervention of a linguist for interpreting results. Special Session: Shared Task - Segmenting Text Into Clauses We invite groups to take part in a shared task: Segmenting a Text Into Clauses (Clausing). Participating groups will be provided with the same training and testing material, and will all use the same evaluation criteria, thus allowing comparison between various learning technologies. After Chunking, the CoNLL-2000 shared task, Clausing can be seen as the next step towards a full parsing. More information on this shared task is available at: http://lcg-www.uia.ac.be/conll2001/clauses/ Invited Session: Learning Computational Grammars There will be a special session devoted to the presentation and discussion of results of the EU Learning Computational Grammars project (Coordinator: John Nerbonne). Project participants include: the University of Groningen (The Netherlands, coordinator), University of Antwerp (Belgium), the University of Tuebingen (Germany), SRI Cambridge (UK), the University College Dublin (Ireland), the University of Geneva (Switzerland), and Xerox Grenoble (France). Invited Speaker (to be announced) SUBMISSIONS Format for Paper Submissions for Main Session Submit an abstract of maximum 1500 words (Postscript or ASCII) by April 6, 2001 electronically to the address below. Authors of accepted abstracts will be invited to produce a full paper to be published in the proceedings of the workshop, which will be available at the workshop for participants, and distributed afterwards by the ACL. Submit main session abstracts to: Walter Daelemans, walter.daelemans at uia.ua.ac.be Centrum Nederlandse Taal en Spraak. Linguistics, Department of Germanic languages and literature UIA, University of Antwerp Universiteitsplein 1, B-2610 Wilrijk, Belgium or R?mi Zajac, zajac at crl.nmsu.edu Computing Research Laboratory New Mexico State University PO Box 30001 Dept. 3CRL Las Cruces NM 88003 USA Format For Shared Task Submissions Submit an abstract of maximum 1500 words describing the learning approach, and your results on the test set by April 6, 2001 to the address below (preferably by email). A special section of the proceedings will be devoted to a comparison and analysis of the results and to a description of the approaches used. Submit shared task submissions to: Erik Tjong Kim Sang, erikt at uia.ua.ac.be Centrum Nederlandse Taal en Spraak Linguistics, Department of Germanic languages and literature UIA, University of Antwerp Universiteitsplein 1, B-2610 Wilrijk, Belgium Important dates Deadline for Abstract Submission: April 6, 2001 Deadline for Shared Task Submission: April 6, 2001 Notification: April 27, 2001 Deadline camera-ready full paper: May 16, 2001 Workshop: July 6/7, 2001 PROGRAMME COMMITTEE Walter Daelemans (co-chair) R?mi Zajac (co-chair) Thorsten Brants (Xerox PARC, USA) Michael Brent (Washington University in Saint Louis, USA) Claire Cardie (Cornell University, USA) James Cussens (University of York, UK) Herve Dejean (University of Tuebingen, Germany) Gregory Grefenstette (Xerox Grenoble, France) Raymond Mooney (University of Texas at Austin, USA) John Nerbonne (Groningen University, Netherlands) Kemal Oflazer (Sabanci University, Turkey) Miles Osborne (University of Edinburgh, UK), David Powers (Flinders University, Australia) Ronan Reilly (University College Dublin, Ireland) Dan Roth (University of Illinois at Urbana-Champaign, USA) Erik Tjong Kim Sang (University of Antwerp, Belgium) Antal van den Bosch (Tilburg University, Netherlands) Yorick Wilks (University of Sheffield, UK) -- ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Thu Feb 22 17:27:40 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Thu, 22 Feb 2001 18:27:40 +0100 Subject: ATALA: Journee sur la structuration de terminologie Message-ID: (English version below) ATALA : Journ?e d'?tude du samedi 10 mars 2001 Structuration de terminologie : objectifs, m?thodes et ?valuation Organis?e par Thierry Hamon et Adeline Nazarenko 9h30 Thierry Hamon (LIPN, Universit? Paris-Nord) Adeline Nazarenko (LIPN, Universit? Paris-Nord) Introduction 10h00 Didier Bourigault (ERSS, Universit? Toulouse le Mirail) C?cile Fabre (ERSS, Universit? Toulouse le Mirail) Extraction de syntagmes et analyse distributionnelle 10h45-11h Pause 11h00 Nathalie Aussenac-Gilles (IRIT, Toulouse) Brigitte Bi?bow (LIPN, Universit? Paris-Nord) Sylvie Szulman (LIPN, Universit? Paris-Nord) Vers un environnement int?gr? pour la struturation de terminologies : Terminae 11h45 Ga?l de Chalendar (LIMSI-CNRS) Brigitte Grau (LIMSI-CNRS) Extraction de terminologies structur?es ? partir de corpus g?n?raux 12h00-14h30 D?jeuner 14h30 Anne Condamines (ERSS, Universit? Toulouse le Mirail) La notion de marqueurs de relation conceptuelle et ses possibilit?s de prise en compte par le TAL 15h15 Patrick S?gu?la (IRIT, Toulouse) Extraction de relations lexicales pour la structuration de terminologie 16h-16h15 Pause 16h15 Farid Cerbah (Dassault Aviation, Saint-Cloud) La structuration de terminologies vue au travers de deux applications 17h Fin de la journ?e d'?tude CHU Piti? - 91 bd de l'H?pital - 75013 Paris Amphi D RdC du b?timent principal, ? gauche des ascenseurs Entr?e libre Adh?sion ? l'association ATALA recommand?e Site ATALA : http://www.atala.org Page Web de cette journ?e : http://www.atala.org/je/je-010310.html ======================================================================= ATALA Workshop. Saturday 10 March 2001 Terminology structuring: purpose, methods and evaluation organised by Thierry Hamon (LIPN, Universit? Paris-Nord) and Adeline Nazarenko (LIPN, Universit? Paris-Nord) Will take place at CHU Piti? - 91 bd de l'H?pital - 75013 Paris Amphitheatre D ---------------------------------------------------------------- Entrance free Applications for membership of ATALA is welcomed http://www.atala.org ----------------------------------------------------------------- 9h30 Thierry Hamon (LIPN, Universit? Paris-Nord) Adeline Nazarenko (LIPN, Universit? Paris-Nord) Introduction 10h00 Didier Bourigault (ERSS, Universit? Toulouse le Mirail) C?cile Fabre (ERSS, Universit? Toulouse le Mirail) Phrase extraction and distributional analysis 10h45-11h Break 11h00 Nathalie Aussenac-Gilles (IRIT, Toulouse) Brigitte Bi?bow (LIPN, Universit? Paris-Nord) Sylvie Szulman (LIPN, Universit? Paris-Nord) Toward an integrated environment for terminology structuring: Terminae 11h45 Ga?l de Chalendar (LIMSI-CNRS) Brigitte Grau (LIMSI-CNRS) Extraction of structured terminologies from general language corpora 12h30-14h30 Lunch 14h30 Anne Condamines (ERSS, Universit? Toulouse le Mirail) Conceptual relationship patterns and their use in NLP 15h15 Patrick S?gu?la (IRIT, Toulouse) Extraction of lexical relations for terminology structuring 16h-16h15 Break 16h15 Farid Cerbah (Dassault Aviation, Saint-Cloud) Terminology structuring in two applicationsx 17h00 End of Workshop ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Thu Feb 22 17:28:06 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Thu, 22 Feb 2001 18:28:06 +0100 Subject: Appel: ACL 2001 2 workshops Message-ID: 1/ ACL/EACL Workshop on Sharing Tools and Resources for Research and Education 2/ Call for papers Workshop on Data-driven MT ACL'2001 Conference ------------------------------------------------------------------- 1/ CALL FOR CONTRIBUTIONS ACL/EACL Workshop on Sharing Tools and Resources for Research and Education Co-organised by ELSNET Toulouse, Saturday 7th July 2001 BACKGROUND: At a workshop at ACL 2000 in Hong Kong dedicated to Infrastructures for Global Collaboration there was an agreement between the main professional organisations in NLP and Speech (ACL and ISCA), and ELSNET, and the other meeting participants, that it would be useful to aim at a broadly supported, joint repository or catalogue for tools and materials for the language and speech communities. An ELSNET-sponsored workshop on educational issues held at EACL99 concluded that certain non-transient infrastructures needed to be instigated to raise the public perception of educational issues in NLP. It also concluded that a repository of shared materials, appropriately indexed for educational usage, would be a useful point of departure. This workshop will build on the consensus reached at these previous workshops. There will be two clear foci: one upon instruments for sharing tools and resources in general that addresses practical problems, and the other upon the technological and infrastructural issues surrounding the educational uses of repositories. Good examples of existing initiatives in this area are among others the ACL Natural Language Software Registry (hosted at DFKI, http://registry.dfki.de) which was set up as a repository for tools for the distinct fields of Human Language Techology (HLT), the ELRA/ELDA, LDC, TELRI and Elsnet resources catalogues and repositories (http://www.icp.inpg.fr/ELRA/, http://www.ldc.upenn.edu/, http://www.telri.de and http://www.elsnet.org/resources.html), OLAC (a worldwide network of language archives at www.language-archives.org), and JEWELS (http://www.elsnet.org/jewels), an as-yet incomplete EU funded website for educational materials in Language and Speech. A third theme concerns how to build upon existing initiatives as sources of data or inspiration. AIM AND SCOPE OF THE WORKSHOP: The main goal of the workshop is to discuss methods for the improvement and extension of existing repositories; the educational uses of repositories; the closer interlinking between different kinds of repositories (tools and resources); global infrastructures for the achievement of joint actions. However, we expect the scope of the workshop to be much wider than that, as the issues addressed are of general interest to everybody who believes that sharing tools and resources is essential for the progress of research and education in our field. Contributions of papers and demonstrations are solicited that address the above themes. The following list of topics is suggestive rather than exhaustive: * Repositories versus catalogues * Mechanisms and infrastructures for sharing and describing content * Repository management * Standards for exchange, description, and annotation * Metadata descriptions * Quality assessment * Structure and content of an NLP/CL repository * Tools and materials for NLP/CL education * Web-based teaching methods for NLP/CL SUBMISSION REQUIREMENTS FOR PAPERS * Electronic submissions only (PostScript, Word, or PDF), following the appropriate ACL latex style or Microsoft Word style. Submissions should not exceed eight (8) pages, including references. You can download the appropriate style or template files using the following link: http://acl2001.dfki.de/style/. In case of problems with the submission format, please contact one of the co-chairs. * Submissions to either co-chair (mros at cs.um.edu.mt and declerck at dfki.de). All submissions will be acknowledged. * Please provide a list of keywords in the separate header page and indicate the best fitting subtopic(s) from the above list. SUBMISSION REQUIREMENTS FOR DEMONSTRATIONS * Demos may be submitted with or without an accompanying paper. * Please write a 2-page description of the demo and send to either co-chair. Please let us know about special hardware requirements over and above the standard PC + beamer without internet access provided by default CONFIRMED COMMITTEE MEMBERS - Thierry Declerck (DFKI) Co-chair (Repository) declerck at dfki.de - Mike Rosner (Malta) Co-chair (Education) mros at cs.um.edu.mt - Steven Bird (U. Penn) - Bill Black (UMIST) (UMIST, Manchester, UK) wjb at co.umist.ac.uk - Gosse Bouma gosse at let.rug.nl (University of Groningen) - Koenraad de Smedt desmedt at uib.no (University of Bergen) - Claire Gardent (CNRS, Nancy) claire.gardent at loria.fr - Steven Krauwer (Utrecht University) steven.krauwer at elsnet.org - Donna Harman (NIST) - Julia Hirschberg (ATT, ISCA) - Jun'ichi Tsujii (Tokyo) - Andy Way (Dublin City University) away at compapp.dcu.ie DEADLINES * Submission Deadline: 6th April 2001 * Notification Date: 27th April 2001 * Camera ready copy due: 16th May 2001 PROVISIONAL WEBSITE http://www.cs.um.edu.mt/~mros/toulouse FOR FURTHER INFORMATION CONTACT Michael Rosner email: mros at cs.um.edu.mt Thierry Duclerc email: declerck at dfki.de ------------------------------------------------------------------- 2/ Call for papers Workshop on Data-driven MT ACL'2001 Conference Toulouse, France Invited speaker: Hermann Ney, RWTH Aachen Deadline for paper submissions: April 6, 2001 Deadline for notification of paper acceptance: April 27, 2001 Deadline for camera-ready papers: May 16, 2001 Workshop Date: July 7, 2001 Details on submissions listed below. With the increased availability of online corpora, data-driven approaches have become central to the NL community. A variety of data-driven approaches have been used to help build Machine Translation systems -- example-based, statistical MT, and other machine learning approaches - and there are all sorts of possibilities for hybrid systems. We wish to bring together proponents of as many techniques as possible to engage in a discussion of which combinations will yield maximal success in translation. We propose to center the workshop on Data Driven MT, by which we mean all approaches which develop algorithms and programs to exploit data in the development of MT, primarily the use of large bilingual corpora created by human translators, and serving as a source of training data for MT systems. We are specifically interested in papers about * statistical machine translation (modeling, training, search) * machine-learning in translation * example-based machine translation * acquisition of multilingual training data * evaluation of data driven methods (also with rule-based methods) * combination of various translation systems; integration of classical rule-based and data driven approaches * word/sentence alignment methods An especially important question that we wish to address is which techniques are best for each of the subparts of a complete MT system - e.g. learning grammars, building lexicons, parsing input data, determining transfer principles, generating target text, etc. We will strongly encourage papers on systems which show demonstrable progress over previously chosen methods, and which have been integrated in an actual end-to-end system. Test results or demos will be given strongest preference for participation. Organizers: Jessie Pinkham, Microsoft Research jessiep at microsoft.com Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Fri Feb 23 12:00:47 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Fri, 23 Feb 2001 13:00:47 +0100 Subject: Appel: MT Summit VIII: workshop Message-ID: ( Apologies if you have already seen an announcement for this workshop ) MT Evaluation: Who Did What To Whom A workshop held in conjunction with Machine Translation Summit VIII Saturday, September 22nd, 2001, Santiago de Compostela, Spain CALL FOR PAPERS Introduction Many measures and methods of evaluating MT systems have been developed over the years. The ISLE project, funded jointly by the European Union and the National Science Foundation of the USA, is continuing with work started in the EU's EAGLES project on systematizing these measures and procedures. This workshop will be the fourth in a series that report on and flesh out portions of the systematization. The main thrust of the work is to build up schemes that classify various aspects of import for MT, including user needs, the suggested system characteristics and associated metrics for measuring each of these. The classification schemes relate to ISO work on software evaluation. The work is intended to be useful to those who are considering using machine translation, those interested in comparative evaluation of several MT systems and to MT system developers. A fuller account of the ISLE evaluation work and an overview of the current classification schemes can be found at http://www.isi.edu/natural-language/mteval/. By the time of the MT Summit, the ISLE project will have organized or been involved in a number of workshops on MT evaluation, namely at LREC in Athens, AMTA in Mexico, Geneva Workshop, and NAACL in Pittsburgh. Participants are encouraged, but not required, to get involved with the Geneva Workshop or NAACL Workshop as these are hands-on exercises in MT. The results of the previous workshops, as possible, will be presented here and feedback based on them serves directly the goal of developing proposals of concrete usefulness to the whole community. This workshop will be seen as a preliminary attempt at reaching conclusions which synthesize results. Information about the previous workshops can be found at: LREC: http://www.icp.grenet.fr/ELRA/lrec2000.html AMTA: http://www.isi.edu/natural-language/conferences/AMTA2000.html NAACL 2001: http://www.cs.cmu.edu/~ref/naacl2001.html MT Evaluation workshop: An invitation to get your hands dirty! http://www.issco.unige.ch/projects/isle/mt-eval-workshop.html, and finally at the MT Summit VIII: http://www.eamt.org/summitVIII. Papers We invite submission of papers along the themes discussed above. The questions and issues to be answered are diverse. All papers on evaluation and evaluation issues will be considered, but preference will be given to papers relating to the ISLE framework. The following questions suggest possible evaluation threads within the framework. * What kind of metrics are useful for what system characteristics? * What system characteristics reflect what user needs? * Is there a radical difference between evaluation focusing on research or development needs and evaluation focusing on end-user needs? * When should real-world data be used, and what is the impact of using it? * What constitutes a valid metric? How can you demonstrate that a metric is valid? * What are the advantages/disadvantages of specific metrics? * What kinds of tools automate the evaluation process? Can the process (or any part of it) be automated? What are the difficulties inherent in choosing particular metrics for automation? * What kinds of tasks are suited to which evaluation schemes? * How can we use the evaluation process to speed or improve the MT development process? * How can we evaluate MT when MT is a small part of the data flow? How independent is MT of the subsequent processing? Cleaning up the data improves performance, but does it improve it enough? How do we quantify that? Submission Guidelines Papers may be submitted electronically to Sandra Manzi, (Sandra.Manzi at issco.unige.ch) by the submission date. The format may be RTF, Microsoft Word, or PostScript. Any specialized fonts should be included in the submission package. Users are advised to follow the main conference formatting as described at: http://www.eamt.org/summitVIII/guidelines.html. Submission for review: papers of no more than 6000 words are expected. Submission for publication: A template will be provided for accepted papers. Important Dates Paper submission deadline April 15, 2001 Notification of acceptance May 31, 2001 Final camera-ready due July 1, 2001 Schedule and Venue This one-day workshop will take place on September 22nd, 2001, after the regular conference. The main conference site contains information about registration and accommodation for both the conference and any satellite events, including this workshop. About Santiago Santiago de Compostela in North West Spain (Galicia) was the most visited pilgrimage shrine in the Middle Ages, and to this day the Road to Santiago is a popular route for walkers through France and northern Spain. The goal is the imposing 11th century cathedral containing the relics of St. James the Great. But the well-preserved historical center of the city offers much more: medieval streets, excellent restaurants, ancient churches, monasteries, palaces, etc. The venue for the conference is the Hostal de los Reyes Cat?licos, founded in 1499 as a Royal hospital for pilgrims; a magnificent building in the Spanish Renaissance style, and now a hotel (the oldest and one of the most beautiful in the world). Those staying at the Hostal will have a once-in-a-lifetime experience, but there is also accommodation nearby in many other good hotels, all within easy walking distance of the center and the Hostal. Santiago de Compostela has its own airport with daily direct flights from Barcelona, Madrid, Brussels and London. Contact Points and Organizing Committee: For any further information, please contact Sandra Manzi, (sandra.manzi at issco.unige.ch) TIM/ISSCO -- University of Geneva 40 blvd du Pont d'Arve CH-1211 GENEVA 4 (Switzerland) Tel: +41-22-705.8680 Fax: +41-22-705.8689 Organizing Committee E. Hovy, ISI, hovy at isi.edu B. Maegaard, CST, bente at cst.ku.dk S. Manzi, ISSCO, sandra.manzi at issco.unige.ch M. King, ISSCO, margaret.king at issco.unige.ch F. Reeder, MITRE, freeder at mitre.org ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/ From alexis.nasr at lim.univ-mrs.fr Fri Feb 23 12:12:40 2001 From: alexis.nasr at lim.univ-mrs.fr (alexis nasr) Date: Fri, 23 Feb 2001 13:12:40 +0100 Subject: Jobs: 5 offres Message-ID: 1/ Computational Linguist, Syntax Classification 2/ Computational Linguist, Text Processing Classification 3/ Linguistic Testing Engineer Classification 4/ Phonetic Lexicographer Classification 5/ Speech Engineer, Prosody Classification Conversay 15375 NE 90th Street Redmond WA 98052 http://www.conversa.com/ ------------------------------------------------------------------------------ 1/ CONVERSAY - Job Description Title Computational Linguist, Syntax Classification Date Updated 14, Dec. 2000 Department Language Development\Core Reports To (Title) Director, Core Engineering Job Description The successful candidate will develop and extend current automatic syntactic analyzers and taggers and be willing to work on text normalization components as well. In addition, s\he should have a predisposition to work with naturally-occurring text corpora and a strongly empirical orientation to syntactic issues. Knowledge, Skills and Abilities * PhD in Linguistics or degree in Computer Science and at least a M.A. in Linguistics * Computational Syntax, NLP, Statistics * Experience with automatic learning and syntactic tagging systems * Knowledge of existing NLP tools * C/C++ * Previous experience with speech processing and applications a plus * Near native knowledge of at least one of the following languages is a strong plus: Portuguese, Dutch, Swedish, Finnish, German, Korean, Japanese, Mandarin or Cantonese Chinese Principal Duties and Responsibilities ? Maintain proprietary Taggers and Parsers. ? Create new NLP tools as required for several diverse languages. ? Help create and maintain text normalization component. Supervision * Able to work with limited supervision. * Position does not involve supervision duties. Decision Making * Adaptable and Creative * Self-motivated Interaction * Able to communicate effectively with scientists and developers. * Willing to work closely with staff syntactician and other linguists and programmers. Equipment * No equipment specifications Physical Requirements * Sustain movements of the fingers, wrists, hands or arms (keyboard work). * Must have the ability to receive detailed information through oral and written communication, to express or exchange information by means of oral and written. Additional Information * Must be willing to relocate to the Seattle/Bellevue/Redmond (WA) area. ------------------------------------------------------------------------------ 2/ CONVERSAY - Job Description Title Computational Linguist, Text Processing Classification Date Updated Department Core Engineering - Language Development Reports To (Title) Manager of Core Technology, Language Development group Job Description The successful candidate will assist in the creation, maintenance and extension of a text/language processing component for multiple languages used by Conversay's proprietary text-to-speech and automatic speech recognition engine. Knowledge, Skills and Abilities (including education) * Thorough understanding of phonology and morphology. * Basic C programming skills and/or experience with scripting languages such as Perl. * Advanced degree in linguistics or computer science (Ph.D. a strong plus). * Knowledge of other areas of linguistics and natural language processing a strong plus. * Familiarity with text normalization/tokenization issues a strong plus. * Knowledge of multiple languages a strong plus (especially Portuguese, Dutch, Swedish, Finnish, German, Korean, Japanese, Mandarin or Cantonese Chinese). * Previous experience with speech applications a plus. Principal Duties and Responsibilities * Extend current text/language processing component to adapt it to different languages, focusing on the following areas: character processing, written word and sentence boundary detection, text normalization, tokenization, text-to-pronunciation, phonology, morphology, lexical access. * Create, extend and maintain new text/language processing modules in the same areas listed above. * Perform any other duties which may be assigned or necessary. Supervision * Position does not involve supervision duties. Decision Making * Must be able to work with limited supervision. * Must be independent, self-motivated and responsible. Interaction * Must be able to interact with linguists, programmers and speech scientists. Equipment * Position does not require knowledge of any specific equipment. Physical Requirements * Sustain movements of the fingers, wrists, hands or arms (keyboard work). * Must have the ability to receive detailed information through oral and written communication, to express or exchange information by means of oral and written. Additional Information * Must be willing to relocate to the Seattle/Bellevue/Redmond (WA) area. ------------------------------------------------------------------------------ 3/ CONVERSAY - Job Description Title Linguistic Testing Engineer Classification Date Updated Department Core Engineering - Language Development Reports To (Title) Mike Aibinder (Director, Core Engineering) Job Description The successful candidate will design, implement, and run suites of automated linguistic tests for Conversay's proprietary text-to-speech and speech recognition system for multiple languages. Knowledge, Skills and Abilities (including education) * Previous industry experience in speech technology / language processing, OR advanced degree in linguistics or a closely related field. * Experience in using scripting or programming languages, especially C, C++, Perl, Visual Basic or Visual Test. * Experience with design & use of automated test tools a plus. * Previous experience with speech applications a strong plus. * Native or near-native knowledge of one of the following languages a strong plus: Portuguese, Dutch, Swedish, Finnish, German, Korean, Japanese, Mandarin or Cantonese Chinese. Principal Duties and Responsibilities * Design and implement automated tools and scripts to evaluate the accuracy and functionality of core language components of Conversay software. For example, write tools, scripts, and expected-behavior frames for testing the text-normalization component. * Work with the Quality Assurance team to design regression tests for core language components. Evaluate bugs reported by QA and direct those bugs to the appropriate members of the Core Engineering team. * Work with the Usability and Quality Assurance team to evaluate user interactions with the language engines, e.g. intelligibility of speech synthesis. * Perform any other duties which may be assigned or necessary. Supervision * Position does not involve supervision duties. Decision Making * Must be able to work with limited supervision. * Must be independent, self-motivated and responsible. Interaction * Must be able to interact with linguists, programmers and speech scientists. * See Principal Duties and Responsibilities above for work with QA and Usability teams. Equipment * Position does not require knowledge of any specific equipment. Physical Requirements * Sustain movements of the fingers, wrists, hands or arms (keyboard work). * Must have the ability to receive detailed information through oral and written communication, to express or exchange information by means of oral and written. Additional Information * Must be willing to relocate to the Seattle/Bellevue/Redmond (WA) area. ------------------------------------------------------------------------------ 4/ CONVERSAY - Job Description Title Phonetic Lexicographer Classification Date Updated Department Core Engineering - Language Development Reports To (Title) Director of Core Engineering Job Description The successful candidate will be responsible for phonetic transcription work in several languages. Duties include: research and analysis to determine specifications for phonetic processing modules, research and purchase of lexical resources, creation and maintenance of lexicons, and analysis of speech and text corpora. The ongoing results of this work will be used in the development of Conversay's proprietary speech recognition and synthesis engines. Knowledge, Skills and Abilities (including education) * Ph.D. in Linguistics with focus on empirical phonetic study * Experience with data and corpus analysis * Native (or near-native) speaker of Japanese or Korean a strong plus * Familiarity with Perl or other scripting/programming languages a strong plus * Familiarity with use of relational databases a strong plus Principal Duties and Responsibilities * Determine phone sets and transcription standards for lexicons in several languages * Determine lexical entries for various application-specific lexicons * Maintain and update existing lexicons * Identify issues and requirements for evaluating phonetic output * Other areas of speech/text collection, analysis, and evaluation as needed Supervision * Position does not involve supervision duties Decision Making * Must be able to work with limited supervision * Must be independent, self-motivated, and responsible Interaction * Must be able to interact with linguists, programmers, speech scientists, and native speakers Equipment * No special knowledge required Physical Requirements * Sustain movements of the fingers, wrists, hands or arms (keyboard work) * Must have the ability to receive detailed information through oral and written communication, to express or exchange information by means of oral and written Additional Information * Must be willing to relocate to the Seattle/Bellevue/Redmond (WA) area ------------------------------------------------------------------------------ 5/ CONVERSAY - Job Description Title Speech Engineer, Prosody Classification Date Updated Department Core Engineering - Language Development Reports To (Title) Director, Core Engineering Job Description The successful candidate will assist in the creation and extension of prosodic components for multiple languages used by Conversay's proprietary text-to-speech and automatic speech recognition engine. Knowledge, Skills and Abilities (including education) * Thorough understanding of prosody and phonology. * C programming. * Advanced degree in linguistics or computer science (Ph.D. a strong plus). * Knowledge of other areas of linguistics and natural language processing a strong plus. * Knowledge of multiple languages a strong plus (especially Portuguese, Dutch, Swedish, Finnish, German, Korean, Japanese, Mandarin or Cantonese Chinese). * Previous experience with speech applications a plus. Principal Duties and Responsibilities * Extend existing prosody module of engine in order to adapt it to different languages. * Create, extend and maintain new prosody module(s). * Perform any other duties which may be assigned or necessary. Supervision * Position does not involve supervision duties. Decision Making * Must be able to work with limited supervision. * Must be independent, self-motivated and responsible. Interaction * Must be able to interact with linguists, programmers and speech scientists. Equipment * Position does not require knowledge of any specific equipment. Physical Requirements * Sustain movements of the fingers, wrists, hands or arms (keyboard work). * Must have the ability to receive detailed information through oral and written communication, to express or exchange information by means of oral and written. Additional Information * Must be willing to relocate to the Seattle/Bellevue/Redmond (WA) area. ___________________________________________________________________ Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://web-lli.univ-paris13.fr/ln/