From alexis.nasr at LINGUIST.JUSSIEU.FR Fri Apr 4 16:26:09 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Fri, 4 Apr 2003 18:26:09 +0200 Subject: Appel: revue TAL : Evolutions en analyse syntaxique Message-ID: [English Version follows] ------------------------------------------------------------------------ [Revue t.a.l.] Appel à soumissions t.a.l. : Évolutions en analyse syntaxique Date limite de soumission : 9 Mai 2003 Numéro dirigé par Éric de la Clergerie (INRIA) et Martin Rajman (EPFL) http://www.atala.org/tal/appel-syntaxe.html Contexte : Analyse syntaxique ------------------------------------------------------------------------ L'analyse syntaxique est une composante très importante dans le traitement automatique des langues. Elle continue de poser de nombreux problèmes que ce soit au niveau des formalismes grammaticaux ou au niveau de la complexité algorithmique, en particulier pour gérer les ambiguïtés. Néanmoins, des progrès ont eu lieu permettant un emploi plus courant et à plus grande échelle de l'analyse syntaxique dans des applications. L'analyse syntaxique regroupe divers courants qui diffèrent sur les objectifs visés et sur les méthodes employées. Les méthodes couvrent par exemple les approches stochastiques, les approches par cascades (de phases d'analyse locale) et les approches plus traditionnelles d'analyse complète (ou profonde). Les objectifs vont de la segmentation en syntagmes à l'analyse profonde avec une grammaire à large couverture, en passant par des analyseurs robustes et/ou superficiels. Néanmoins cette diversité dans les méthodes et objectifs reflète une certaine complémentarité plutôt qu'une opposition absolue. Le foisonnement des formalismes syntaxiques est aussi important avec cependant des points de convergence. Ceux ci rendent ainsi possible des conversions entre formalismes syntaxiques (par exemple entre TAG et HPSG ou HPSG et CFG) ou vers des formalismes plus «opérationnels». Certaines techniques d'analyse sont « génériques » et utilisables pour plusieurs formalismes. Certains systèmes se veulent multi-formalismes, reposant sur une infrastructure générique et efficace (pour l'indexation, la gestion des ambiguïtés, l'unification, gestion de la mémoire par partage ou copie de structures,...). Enfin la notion de lexicalisation des grammaires transcende largement les formalismes. D'autre part, la généralisation progressive des analyseurs syntaxiques soulève la question de leur évaluation. Thème : ------------------------------------------------------------------------ L'objectif de ce numéro est de mieux comprendre l'ensemble des approches et techniques utilisées en analyse syntaxique et surtout d'en mieux cerner les convergences et complémentarités. La liste suivante non exhaustive énumère divers sujets pertinents pour cet appel. - Convergence de formalismes syntaxiques - Conversions entre formalismes - Formalismes opérationnels ou descriptifs - Convergence et complémentarité des approches d'analyse syntaxique - Robustesse (traitement des mots inconnus, correction d'erreurs) - Lexicalisation - Intégration de méthodes stochastiques - Analyse en cascade ou approches globales - Évolution des approches pour de nouveaux formalismes - Optimisations (génériques) des analyseurs - stratégies d'analyse - gestion de l'ambiguïté - techniques d'indexation - gestion mémoire (partage et copie de structures) - Passage aux grammaires à large couverture - efficacité des analyseurs - maintenance et modularité - Évaluation des analyseurs Comité de lecture spécifique ------------------------------------------------------------------------ Pierre Boullier (INRIA, Rocquencourt) John Carroll (Université du Sussex, GB) Jean-Pierre Chanod (XRCE, Grenoble) Alexandra Kinyon (Université de Pennsylvanie, USA) Guido Minnen (Motorola, USA) Alexis Nasr (LATTICE, Paris) Mark-Jan Nederhof (Université de Groningen, Pays-Bas) Gertjan van Noord (Université de Groningen, Pays-Bas) Patrick Paroubek (LIMSI, Orsay) Gerald Penn (Université de Toronto, Canada) Anoop Sarkar (Université Simon Fraser, Canada) Giorgio Satta (Université de Padoue, Italie) Manuel Vilares (Université de Vigo, Espagne) David Weir (Université du Sussex, GB) Rémi Zajac (Systran Software, USA) Format ------------------------------------------------------------------------ Les articles (25 pages maximum) seront soumis au format Word, LaTeX, Postscript ou PDF. Les feuilles de style sont disponibles chez HERMES Langue ------------------------------------------------------------------------ Les articles peuvent être écrits en français ou en anglais. Cependant, les soumissions en anglais ne sont acceptées que pour les auteurs non francophones. Calendrier ------------------------------------------------------------------------ La date limite de soumission est fixée au 9 Mai 2003. Les personnes qui ont l'intention de soumettre un article sont invitées à prendre contact avec Éric de la Clergerie (Eric.De_La_Clergerie at inria.fr). Les articles seront relus par un membre du comité de rédaction de la revue TAL et par deux relecteurs du comité de lecture constitué spécifiquement par les coordinateurs pour ce numéro. La décision du comité de rédaction sera transmise aux auteurs avant le 1er Juillet 2003. La version définitive des articles acceptés sera à remettre pour le 1er Octobre 2003 pour une publication prévue fin 2003. Envoi des articles ------------------------------------------------------------------------ Les articles (25 pages maximum, au format Hermès) doivent être envoyés par voie électronique à Eric.De_La_Clergerie at inria.fr ou par voie postale (version papier en cinq exemplaires) à l'adresse suivante : Éric de la Clergerie INRIA Rocquencourt Domaine de Voluceau - B.P. 105 78153 Le Chesnay Cedex, France ====================================================================== Call for papers for the special issue of the TAL journal Title: Evolutions in Parsing Submission deadline: May 9th 2003 Guest Editors: Éric de la Clergerie (INRIA, France) Martin Rajman (EPFL, Switzerland) http://www.atala.org/tal/appel-syntaxe.html ------------------------------------------------------------------------------ Parsing is a very important component in Natural Language Processing. It still raises many problems, for instance at the level grammatical formalisms or at the level of the algorithmic complexity, especially to handle ambiguity. However, because of recent advances, parsers are nowadays more and more widely used in large scale applications. Many approaches exist in the Parsing community that differ on the methods and objectives. The methods include for instance stochastic parsing, local parsing cascades, or more traditional complete or deep parsing. Objectives range from segmentation into chunks to deep parsing based on wide coverage grammars, including shallow and/or robust parsing. Anyway, these various methods and objectives are not necessarily in opposition and may be perceived as complementary. Despite the large number of existing grammatical formalisms, there are hints of convergences between them which open ways for (partial) conversions between formalisms (for instance between TAG and HPSG or HPSG and CFG) or toward "operational" formalisms. Also, some parsing techniques are "generic" and may be applied for several formalisms. Some parsing systems also aim to be multi-formalisms, relying on generic and efficient infrastructures (indexing, memory management by structure sharing or copying, powerful unification). Finally, the notion of lexicalization is present in most formalisms. Last but not least, the generalization of parsers raises the issue of their evaluation. ------------------------------------------------------------------------------ Themes: The main objective of this special issue is a better understanding of the various approaches and techniques found in Parsing, highlighting the convergences and complementarities that may exist between them. We welcome works on any of the following issues. * Convergence between grammatical formalisms * conversions of formalisms * operational formalisms vs declarative ones * Convergence and complementarity in parsing approaches * robustness (unknown words, error corrections) * lexicalization * Integration of stochastic methods * Cascade parsing vs one-pass parsing * Evolution of parsing techniques for new formalisms * (generic) Optimizations in Parsing * parsing strategies * ambiguity management * chart indexing * memory management (structure sharing and copying) * Wide coverage grammars * parsing efficiency * maintenance and modularity * Parsing evaluation Reviewers ------------------------------------------------------------------------------ Pierre Boullier (INRIA, France) John Carroll (University of Sussex, UK) Jean-Pierre Chanod (XRCE, France) Alexandra Kinyon (University of Pennsylvania, USA) Guido Minnen (Motorola, USA) Alexis Nasr (LATTICE, France) Mark-Jan Nederhof (University of Groningen, NL) Gertjan van Noord (University of Groningen, NL) Patrick Paroubek (LIMSI, France) Gerald Penn (University of Toronto, Canada) Anoop Sarkar (Simon Fraser University, Canada) Giorgio Satta (University of Padua, Italy) Manuel Vilares (University of Vigo, Spain) David Weir (Université of Sussex, UK) Rémi Zajac (Systran Software, USA) Format ------------------------------------------------------------------------------ Papers (25 pages maximum) may be submitted in Word, LaTeX, Postscript or PDF. The style sheets are available at HERMES Language ------------------------------------------------------------------------------ Papers may be written either in French or in English (non-French speaking authors only) Schedule ------------------------------------------------------------------------------ The submission deadline is May 9th 2003. People intending to submit a paper should contact Éric de la Clergerie (Eric.De_La_Clergerie at inria.fr). Articles will be reviewed by a member of the editorial board of the journal (http://www.atala.org/tal/redaction.html) and two external reviewers chosen by the editors of the special issue. Editorial board decisions and referees' reports will be transmitted to the authors by July 1st, 2003. Final versions of accepted papers will be required by October 1st, 2003. Publication is planned for the end of 2003. Submission ------------------------------------------------------------------------------ Submissions (25 pages maximum, following the Hermes style sheet) should be sent either electronically (Eric.De_La_Clergerie at inria.fr), or by surface mail (five copies) to Éric de la Clergerie INRIA Rocquencourt Domaine de Voluceau - B.P. 105 78153 Le Chesnay 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrainée par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adhésion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Fri Apr 4 16:26:13 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Fri, 4 Apr 2003 18:26:13 +0200 Subject: Conf: GDR 2220 : La productivite : regards actuels Message-ID: La productivité : regards actuels lundi 12 mai 2003 CHU Pitié-Salpétrière, salle 408, 4e étage 105, boulevard de l'Hôpital 75013 - Paris métro : Saint-Marcel http://www.biomath.jussieu.fr/adresse-chu-pitie.html Entrée libre L'action 5 du GDR 2220 « Description et modélisation en morphologie » vous invite à la journée internationale sur la productivité qu'elle organise le lundi 12 mai 2003. Vous trouverez les résumés des communications sur le site du GDR : http://gdr-morphologie.linguist.jussieu.fr/journee-productivite . Pour tout renseignement, contactez Georgette Dal : mailto:dal at univ-lille3.fr . Programme : 9h15-9h30 - Ouverture de la journée 9h30-10h10 - Georgette Dal [UMR 8528 (CNRS & Un. Lille 3) & GDR 2220] La productivité : quelques préalables 10h10-11h10 - R. Harald Baayen [Interfaculty Research Unit for Language and Speech (IWTS), University of Nijmegen & Max Planck Institute for Psycholinguistics] [titre non encore communiqué] 11h10-11h30 - Pause 11h30-12h30 - Georgette Dal, Bernard Fradin [UMR 7110 (CNRS & Un. Paris 7) & GDR 2220], Nabil Hathout [UMR 5610 (CNRS & Un. Toulouse-le Mirail) & GDR 2220] & Fanny Meunier [UMR 5596 (CNRS & Un. Lyon 2) & GDR 2220] Productivités comparées : le cas de la suffixation en ET 12h30-14h00 - Déjeuner 14h00-15h00 - Davide Ricca & Livio Gaeta [Dipartimento di Scienze del Linguaggio, Universita' di Torino] Quantitative methods and Italian word formation: A variable-corpus approach to productivity 15h00-16h00 - Anke Lüdeling [Institut für deutsche Sprache und Linguistik, Humboldt-Universität zu Berlin] The interaction of qualitative and quantitative aspects of productivity 16h00-16h20 - Pause 16h20-17h20 - Natalia Grabar [ERM 202, INSERM & GDR 2220], Fiammetta Namer [UMR 7118 & GDR 2220] & Pierre Zweigenbaum [ERM 202, INSERM & GDR 2220] Adjectifs dénominaux: quelle productivité pour quels corpus? 17h20-17h45 - Clôture de la journée ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrainée par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adhésion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Fri Apr 4 16:26:16 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Fri, 4 Apr 2003 18:26:16 +0200 Subject: Appel: SEPLN 2003 Message-ID: Second Call for Proposals SEPLN 2003 Second Call for Proposals SEPLN 2003 XIX CONGRESO DE LA SOCIEDAD ESPAÑOLA PARA EL PROCESAMIENTO DEL LENGUAJE NATURAL (SEPLN) (19th Conference of the Spanish Society for Natural Language Processing - SEPLN) September 10-12, 2003 Universidad de Alcalá de Henares Alcalá de Henares (Madrid) http://oesi.cervantes.es/sepln Introduction The 19th Conference of the Spanish Society for Natural Language Processing (SEPLN) will take place on September 10-12, 2003 in Alcalá de Henares (Madrid, Spain). As in previous editions, the aim of SEPLN for this Conference is to promote the dissemination of research, development and innovation activities conducted by Spanish and foreign researchers in the field of Natural Language Processing (NLP). The conference will provide a forum for discussion and communication to facilitate an effective exchange of knowledge and scientific materials that are necessary for promoting the publication of relevant work and the establishment of means of collaboration with national and international Institutions that are active in this field. Objectives The main motivation of this conference is to provide the business and scientific communities with an ideal forum for presenting their latest research work and developments in the field of Natural Language Processing, as well as to demonstrate the possibilities offered by these solutions and to know about new projects. Consequently, the 19th SEPLN Conference is a meeting place for presenting results and exchanging ideas concerning the present state of development in this field of knowledge. Furthermore, there is the intention of meeting the goal, achieved in previous editions, of identifying future paths for basic research and foreseen software applications, in order to compare them against the market needs. Finally, the conference intends to be an appropriate forum in helping new professionals to become active members in this field. Topics Researchers and businesses are encouraged to send communications, project abstracts or demonstrations related to any of the following topics: Linguistic, mathematic and psycholinguistic models of language Corpus linguistics Monolingual and multilingual information extraction and retrieval Formalisms and grammars for morphological and syntactical analysis Computational Lexicography Monolingual and multilingual text generation Machine translation Speech synthesis and recognition Semantics, pragmatics and discourse Word sense disambiguation NLP industrial applications Automatic textual content analysis Structure of the Conference The Conference will last three days, with sessions dedicated to presenting papers, ongoing research projects, prototype product demonstrations or products connected with topics addressed in the conference. Scientific activities will be complemented by social and tourist activities, allowing attendants to gain a better understanding about the social and cultural dimensions of Alcalá de Henares. Communications Authors are encouraged to send theoretical or system-related proposals, to be presented at the demonstration sessions, earlier than May 16, 2003. Proposals must meet certain format and style requirements Both the delivery and revision of proposals will be done exclusively in electronic format (PostScript or PDF). Proposals will include a title, the complete names of the authors, their address, telephone, fax and e-mail. Proposals will meet the following requirements (concerning the final version, please check the "publication format" section): The proposals will be presented in Spanish or English Inclusion of an abstract (maximum 150 words) Related topic Overall maximum length will be 3,500 words (including the abstract) The proposals will be anonymously revised. Therefore, two separate files will be submitted, one will only include the title and author details, the other will only include the title and the rest of the proposal Final versions (after notification of acceptance) will follow the style requirements that are described in the publication format section in this website Authors will submit their proposals through the following web system: https://chair.dlsi.ua.es/sepln03/submit.html Projects and Demos As in previous editions, the organizers encourage participants to give oral presentations of projects and demos. Depending on the estimated number of oral presentations, any session may be reserved to this purpose. Proposals must meet certain format and style requirements for presentations. For oral presentation of projects to be accepted, the following information must be included: - Project title - Funding institution - Participant groups in the project - Name, affiliation, e-mail and phone number of the project director - Abstract (2 pages maximum) - If a demonstration is to be performed, further information must be included, as indicated below For demonstrations to be accepted, the following information is mandatory: - Name, affiliation, e-mail and phone number of the authors - Abstract (2 pages maximum) - Time estimation for the whole presentation - This information must be received by June 10, 2003 Publication Format The final version of the article will be sent before June 27, 2003 through a web system: https://chair.dlsi.ua.es/sepln03/submit.html - Documents must not include headers or footings - Maximum length will be 8 pages DIN A4 (210 x 297 mm), included references and figures. - In the case of demonstrations and projects, maximum length will be 2 pages. Articles will be sent in Postscript or PDF format. LaTeX format Authors using LaTeX format may download from the Conference website the following style package zip file: latex_new.zip which contains document and bibliography styles, as well as an example showing existing possibilities. Word format Authors using Microsoft Word or compatible may download from the Conference website the following zip file: word_new.zip which includes a pattern file in RTF format and an example showing existing editing possibilities. Important Dates Dates for submission and notifications of acceptance: - Deadline for submitting abstracts: May 16, 2003 - Notification of acceptance: June 20, 2003 - Deadline for submitting the final version: June 27, 2003 - Deadline for submitting projects and demos: June 10, 2003 Program Committee Chairman: Prof. Maximiliano Saiz Noeda (Universitat d'Alacant) max at dlsi.ua.es Members: Prof. José Gabriel Amores Carredano (Universidad de Sevilla) Prof. Toni Badia i Cardús (Universitat Pompeu Fabra) Prof. Manuel de Buenaga Rodríguez (Universidad Europea de Madrid) Prof.ª Irene Castellón Masalles (Universitat de Barcelona) Prof.ª Arantza Díaz de Ilarraza (Euskal Herriko Unibertsitatea) Prof. Antonio Ferrández Rodríguez (Universitat d'Alacant) Prof. Mikel Forcada Zubizarreta (Universitat d'Alacant) Prof.ª Ana María García Serrano (Universidad Politécnica de Madrid) Prof. Koldo Gojenola Galletebeitia (Euskal Herriko Unibertsitatea) Prof. Xavier Gómez Guinovart (Universidade de Vigo) Prof. Julio Gonzalo Arroyo (Universidad Nacional de Educación a Distancia) Prof. José Miguel Goñi Menoyo (Universidad Politécnica de Madrid) Prof. Joaquim Llisterri (Universitat Autònoma de Barcelona) Prof. Javier Macías Guarasa (Universidad Politécnica de Madrid) Prof. José B. Mariño Acebal (Universitat Politècnica de Catalunya) Prof.ª M. Antonia Martí Antonín (Universitat de Barcelona) Prof.ª Lidia Ana Moreno Boronat (Universitat Politècnica de Valencia) Prof. Lluis Padró (Universitat Politècnica de Catalunya) Prof. Manuel Palomar Sanz (Universitat d'Alacant) Prof. José Manuel Pardo Muñoz (Universidad Politécnica de Madrid) Prof.ª Natividad Prieto Sáez (Universitat Politècnica de Valencia) Prof. Germán Rigau (Universitat Politècnica de Catalunya) Prof. Horacio Rodríguez Hontoria (Universitat Politècnica de Catalunya) Prof. Kepa Sarasola Gabiola (Euskal Herriko Unibertsitatea) Prof. L. Alfonso Ureña López (Universidad de Jaén) Prof.ª Mª Felisa Verdejo Maillo (Universidad Nacional de Educación a Distancia) Prof. Manuel Vilares Ferro (Universidade de Vigo) Organising Committee Chairman: Mr. Jesús Antonio Cid Martínez, Academic Director at Instituto Cervantes Coordinator: Ms. Isabel Bermejo Rubio, Responsible for the Bureau of Spanish in the Information Society - OESI - at Instituto Cervantes Members: Ms. Eva Mª García García, Technician at OESI, Instituto Cervantes Ms. Raquel Tapias Aparicio, Technician at OESI, Instituto Cervantes Mr. John Michael Urresti Graña, Technician at OESI, Instituto Cervantes Collaborators: Ms. Eva Mª Gómez Gómez, Collaborator at OESI, Instituto Cervantes Ms. Rosario Guijarro Huerta, Collaborator at OESI, Instituto Cervantes Further Information Full information is available at the official website of the Conference: http://oesi.cervantes.es/sepln You may also contact the coordinator at any of the following addresses: Secretary of the 19th SEPLN Conference Conference coordinator: Ms. Isabel Bermejo Rubio Oficina del Español en la Sociedad de la Información C/ Libreros, 23 28801 Alcalá de Henares (Madrid) Spain Tel.: +34 91 888 72 94 Fax: +34 91 888 18 26 E-mail: sepln at cervantes.es Conference website: http://oesi.cervantes.es/sepln ------------------------------------------------------- ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrainée par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adhésion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Fri Apr 4 16:26:19 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Fri, 4 Apr 2003 18:26:19 +0200 Subject: Appel: CSSP 2000 Message-ID: ======================================================================= We apologize if you receive this more than once. ======================================================================= ___ ___ ___ ____ ___ ___ ___ ___ / __)/ __)/ __)( _ \ (__ \ / _ \ / _ \ (__ ) ( (__ \__ \\__ \ )___/ / _/ ( (_) )( (_) ) (_ \ \___)(___/(___/(__) (____) \___/ \___/ (___/ THE FIFTH SYNTAX AND SEMANTICS CONFERENCE IN PARIS OCTOBER 2-4, 2003 SECOND CALL FOR PAPERS THEMATIC SESSION The Syntax and Semantics of Number INVITED SPEAKERS Nirit Kadmon (Tel Aviv University) Manfred Krifka (Humboldt University - Berlin) Robert Levine (Ohio State University) Mark Steedman (Edinburgh University) Anne Zribi-Hertz (Paris 8 University) SUBMISSION DEADLINE April 30, 2003 The fifth Syntax and Semantics Conference in Paris (CSSP 2003) will take place at Paris 7 University, on October 2-4, 2003. The conference welcomes papers combining empirical inquiry and formal explicitness. It aims at favouring comparisons between diverse formal theories of syntax and semantics. The domains of inquiry are syntax, semantics, and the syntax-semantics interface. CSSP conferences combine a general session and a thematic session. The theme for the CSSP 2003 thematic session is the syntax and semantics of Number. Prospective speakers are invited to submit an abstract, no more than two pages long (including figures and references), written in French or English. Abstracts should be sent by e-mail (plain ASCII, rtf, ps or pdf) before April 30 to: cssp03 at linguist.jussieu.fr Authors who are not able to send an electronic version should send two hard copies (one anonymous, one non-anonymous) of the abstract to: Colloque de Syntaxe et Semantique a Paris - Universite Paris 7 - UFRL, Case 7003 - 2 Place Jussieu - 75251 Paris-Cedex 05 - France For more information: Web site: http://www.llf.cnrs.fr/CSSP E-mail: cssp03 at linguist.jussieu.fr ORGANISING COMMITTEE: Claire Beyssade (CNRS-J. Nicod), Olivier Bonami (Chair, Rennes 2), Patricia Cabredo Hofherr (CNRS-Paris 8), Daniele Godard (CNRS-Paris 7) SCIENTIFIC COMMITTEE: Claire Beyssade (CNRS-J. Nicod), Olivier Bonami (Rennes 2), Patricia Cabredo Hofherr (CNRS-Paris 8), Francis Corblin (Paris 4), Daniele Godard (CNRS-Paris 7), Jean-Marie Marandin (CNRS-Paris 7) -- ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain�e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh�sion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Fri Apr 4 16:26:23 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Fri, 4 Apr 2003 18:26:23 +0200 Subject: Appel: ACL-SIGSEM Workshop on The Linguistic Dimensions of Prepositions ... Message-ID: <<< NEW DEADLINE: April 25th !! >>>> Call for Papers : ACL-SIGSEM Workshop on The Linguistic Dimensions of Prepositions and their Use in Computational Linguistics Formalisms and Applications. September 4-6, 2003, Toulouse, France Endorsed by SIGSEM, the ACL's Special Interest Group in Computational Semantics. A great deal of attention has been devoted in the past ten years in the linguistic and computational linguistics communities to the syntax and the semantics of nouns, verbs and also, but to a lesser extent, to adjectives. Related phenomena such as quantification or tense and aspect have motivated a number of in-depth studies and projects. In contrast, prepositions have received less attention. The reasons are quite clear: prepositions are probably the most polysemic category, possibly more so than adjectives, and linguistic realizations are extremely difficult to predict, not to mention the difficulty of identifying cross-linguistic regularities. Let us mention, however, several projects devoted to prepositions expressing space, time and movement in AI and in NLP, and also the development of formalisms and heuristics to handle PP attachment ambiguities. Let us also mention the large number of studies in psycholinguistics and in ethnolinguistics around specific preposition senses. Finally, prepositions seem to reach a very deep level in the cognitive-semantic structure of the brain: cognitive grammar developers often use prepositions in their metalanguage, in order to express very primitive notions. An important and difficult question to address, is whether these notions are really primitive or can be decomposed and lexically analysed In argument structure, prepositions often play the crucial role of a mediator between the verb's expectations and the semantics of the nominal argument. The verb-preposition-noun semantic interactions are very subtle, but totally crucial for the development of an accurate semantics of the proposition. Let us note that a number of languages have postpositions or other markers like case instead of prepositions that play a quite similar role. Finally, languages like English have verbal compounds that integrate prepositions (compositionally or as collocations) while others, like Romance languages or Hindi either incorporate the preposition or include it in the prepositional phrase. All these configurations are semantically as well as syntactically of much interest. Prepositions turn out to be a very useful category in a number of applications such as indexing and knowledge extraction since they convey basic meanings of much interest like instruments, means, comparisons, amounts, approximations, localizations, etc. They must necessarily be taken into account---and rendered accurately---for effective machine translation and lexical choice in language generation. Prepositions are also closely related to semantic structures such as thematic roles, semantic templates or frames. From a linguistic perspective, several investigations have been carried out on quite diverse languages, emphasizing e.g., monolingual and cross-linguistic contrasts or the role of prepositions in syntactic alternations. These observations cover in general a small group of closely related prepositions. The semantic characterization of prepositions has also motivated the emergence of a few dedicated logical frameworks and reasoning procedures. The aim of this workshop is to bring together linguists, NLP researchers and practitioners, and AI people in order to define a common ground, to advance the state-of-the-art, to identify the primary issues and bottlenecks, and to promote future collaborations. If appropriate, the workshop will also establish a working group and the development of projects and resources. Paper presentations Both short research notes (3 pages) and longer conference-style papers (up to 10 pages) submissions as well as working session proposals (1 page proposal on a precise topic) are welcome. Papers must be in .ps, .pdf or .doc formats. The 12 point Times new Roman font is preferred, leave about 2.5 cm margins on both sides. More precise formatting instructions will be given for final versions, since a book publication is under preparation. Paper must be sent in electronic form to: stdizier at irit.fr The main topics are: - The syntax of prepositions: formal or descriptive syntax, prepositions in alternations, principles in the syntax of PPs, syntactic and semantic restrictions. General syntactic-semantic principles. Postpositions or other equivalent markers (e.g. case). - Polysemy of prepositions, identification and classification of preposition senses, contrastive uses, metaphorical uses, semantic and cognitive foundations for prepositions. - Descriptions: Potential WordNet / EuroWordNet descriptions of preposition uses, productive uses versus collocations, multi-lingual descriptions: mismatches, incorporation, divergences. Prepositions and thematic roles, prepositions in semantic frameworks (e.g. Framenet.). - Cognitive or logic-based formalisms for the description of the semantics of prepositions, in isolation, and in composition/confrontation with the verb and the NP. Compositional semantics. Logical and reasoning aspects. - The role of prepositions in applications, in particular: * in machine translation * in information extraction * in lexicalization in language generation. - Corpus-based studies that support or challenge any of the approaches described above. - Lexical knowledge bases and prepositions. Prepositions in AI, KR and in reasoning procedures. Deadlines Submission deadline: April 25th, 2003 <<<<< NEW DEADLINE >>>>>> Notification to authors: May 30th Final paper due July 1st (a book publication is under preparation) Registration preferably before July 7th. (to be confirmed) Registration frees will be kept as low as possible, around 100 Euros with lunch. Programme Committee: Nicholas Asher (Austin) Pushpak Bhattacharyya (IIT Mumbai) Harry Bunt (Tilburg) Nicoletta Calzolari (Pisa) Bonnie Dorr (Maryland) Christiane Fellbaum (Princeton) Claire Gardent (CNRS Nancy) Betsy Klipple (Upenn) Alda Mari (ENST Paris) Palmira Marraffa (Lisboa) Martha Palmer (Upenn) James Pustejovsky (Brandeis) Patrick Saint-Dizier (Chair, IRIT, Toulouse) Gloria Vazquez (Lerida) Laure Vieu (IRIT, Toulouse) Contacts : Submissions and inquiries : stdizier at irit.fr and submissions also to : patrick_saintdizier at yahoo.fr Local organizing committee : Farah Benamara, Patrick Saint-Dizier WEB site: www.irit.fr/cgi-bin/voir-congres ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain�e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh�sion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Fri Apr 4 16:26:26 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Fri, 4 Apr 2003 18:26:26 +0200 Subject: Appel: Eurospeech'2003 Message-ID: Dear Colleagues, Given the recent cancelation of ICASSP'03, the Eurospeech'2003 Organizing Committee decided to slightly extend the paper submission deadline until Sunday, April 6, midnight. Please, be aware though that there will be no further extension and that this is the actual final submission deadline! This should thus give you the opportunity to publish updated results related to a planned ICASSP presentation. Of course, this is not an invitation to re-submit the same paper (which is "illegal", and will be closely checked), but to offer you an opportunity to present an updated/enhanced version of it. Also, I think that there were 2 ICASSP special sessions related to speech processing. Of course, again, papers have been published and cannot be "re-cycled". However, if you feel like you missed the opportunity for discussions, etc, and if you believe that the community could benefit from a special session on the same topic at Eurospeech, please let me know. Again, this possibility will be considered at the sole condition that papers would present updated information. Eurospeech special sessions have been selected already and are currently adverstised on the Eurospeech web site, but we would see together what we could do to help you organize this. Best regards, --Herve Bourlard Eurospeech'2003, General Chair ==================================================================================== Eurospeech 2003 / Interspeech 2003 http://www.eurospeech2003.org/ September 1--4, 2003 Geneva, Switzerland CALL FOR PAPERS CALL FOR TUTORIALS CALL FOR SPECIAL SESSIONS ISCA, toghether with the the Eurospeech 2003 /Interspeech 2003 organizing committee, would like to encourage submission of papers for the upcoming conference. The scientific topics are : * Linguistic Modelling of Spoken Language * Phonetics and Phonology * Speech Production * Speech Perception * Discourse and Dialogue * Signal Analysis, Processing and Feature Estimation * Speech Recognition and Understanding * Speaker Authentication * Speech Generation and Synthesis * Spoken Dialogue Systems * Speech Coding and Transmission * Resources, Assessment and Standards * Applications * Education * Other (please specify) No previously published papers should be submitted. Please follow the submission guidelines provided at the URL: http://www.eurospeech2003.org/papers/ TUTORIALS We encourage proposals for half-day pre-conference tutorials. Between 4 and 8 tutorials will be offered on August 31, 2003. Those interested in organizing a tutorial should send a one-page description to Andrzej Drygajlo (andrzej.drygajlo at epfl.ch), with cc to organisers at eurospeech2003.org by January 15. SPECIAL SESSIONS Eurospeech 2003 also welcomes proposals for special sessions. Each special session should consist of 6 invited papers. The topics of the special sessions should be important, new, emerging areas of interest to the signal processing community, yet have little overlap with the regular sessions. They could also be those investigated by members of other societies that are becoming of keen interest to the speech and language community. See the Eurospeech'03 web page at http://www.symporg.ch/eurospeech/Special_session.asp for guidelines. IMPORTANT DATES: Proposals for Tutorials due by: January 15, 2003 Proposals for Special Sessions due by: January 30, 2003 Full and final paper submission deadline: March 28, 2003 Notification of paper acceptance/rejection: June 9, 2003 Early registration: before June 16th, 2003 Conference programme: as of July 15th, 2003 For further information, please refer to the conference web site, at the URL: http://www.eurospeech2003.org/ -- Please see http://www.idiap.ch/local/mailing-lists/ for more infos on IDIAP Mailing lists. ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain�e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh�sion : http://www.atala.org/ ------------------------------------------------------------------------- From thierry.hamon at LIPN.UNIV-PARIS13.FR Thu Apr 10 09:15:22 2003 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Thu, 10 Apr 2003 11:15:22 +0200 Subject: Job: SYSTRAN Message-ID: From: Christiane Panissod Message-ID: <3E91AB4C.8AB2A14A at systran.fr> ********************************************** SYSTRAN, leader in automatic translation solutions, has a position available for a Dutch language trainee (full or part time, from April, 15). The person hired will assist in the development of automatic language translation software at Systran. The work involves creation of electronic dictionaries, assistance in creating linguistic rules, and evaluation of translation results etc. Qualifications : - native command of Dutch - extensive knowledge of the grammar of Dutch - familiarity with linguistic concepts - fluency in English and/or French - basic computer skills required - experience in translation would be helpful Contact C Panissod Mail: panissod at systran.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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain�e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh�sion : http://www.atala.org/ ------------------------------------------------------------------------- From thierry.hamon at LIPN.UNIV-PARIS13.FR Thu Apr 10 09:15:22 2003 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Thu, 10 Apr 2003 11:15:22 +0200 Subject: Q: Corpus of Modern Standard Arabic Message-ID: From: Eric Atwell Message-ID: X-url: http://www.personal.leeds.ac.uk/~scsla/index.html X-url: http://www.computingLEEDS.ac.uk Dear All, I plan to develop a corpus of Modern Standard Arabic, and I would like your views on the types of texts that should be included in this corpus. Answering my questionnaire on this website http://www.personal.leeds.ac.uk/~scsla/index.html will enable me to get a clear idea of the kinds of texts to collect. Also, I welcome any contributions of Arabic text or speech. Thank you Dr Latifa Al-Sulaiti, CVL: Computer Vision and Language research group School of Computing, University of Leeds, LEEDS LS2 9JT TEL: 0113-3437288 FAX: 0113-3435468 EMAIL: latifa at comp.leeds.ac.uk Visit http://www.computingLEEDS.ac.uk - our newsletter for industry ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain�e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh�sion : http://www.atala.org/ ------------------------------------------------------------------------- From thierry.hamon at LIPN.UNIV-PARIS13.FR Thu Apr 10 09:15:22 2003 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Thu, 10 Apr 2003 11:15:22 +0200 Subject: Conf: IWPT 2003 Message-ID: From: Guy Perrier Message-ID: <3E93BEA8.5080002 at loria.fr> X-url: http://iwpt03.loria.fr/ X-url: http://parlevink.cs.utwente.nl/sigparse/ C a l l f o r P a r t i c i p a t i o n IWPT 2003 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 8th International Workshop on Parsing Technologies ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Sponsored by ACL/SIGPARSE 23-25 April 2003 Nancy, France http://iwpt03.loria.fr/ ~~~~ Nancy, "City of Art and History", the historical capital of Lorraine (the north-eastern part of France) welcomes you to the 8th International Workshop on Parsing Technologies. The Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA) in Nancy, France, will host the 8th International Workshop on Parsing Technologies (IWPT'03) from 23 to 25 April, 2003. IWPT'03 continues the tradition of biennial workshops on parsing technology organised by SIGPARSE, the Special Interest Group on Parsing of the Association for Computational Linguistics (ACL). This workshop series was initiated by Masaru Tomita in 1989. The first workshop, in Pittsburgh and Hidden Valley, was followed by workshops in Cancun (Mexico) in 1991; Tilburg (Netherlands) and Durbuy (Belgium) in 1993; Prague and Karlovy Vary (Czech Republic) in 1995; Boston/Cambridge (Massachusetts) in 1997; Trento (Italy) in 2000, and Beijing (China) in 2001. ******************************************** * INVITED SPEAKERS: * * * * Gregory Grefenstette (Clairvoyance Corp) * * Eugene Charniak (Brown University) * * * ******************************************** Program: -------- Three days of invited talks, long papers, short papers and posters and discussions. invited talks: -------------- Eugene Charniak (Brown University), Syntax-based Language Models for Statistical Machine Translation Gregory Grefenstette (Claivoyance Corporation, Pittsburgh), Why Parse? Statistical Processing or Symbolic Processing. accepted papers: ---------------- Miguel A. Alonso, Víctor J. Díaz, Parsing Tree Adjoining Grammars and Tree Insertion Grammars with simultaneous adjunctions. Pierre Boullier, Supertagging: A non-Statistical Parsing-based Approach. Denis Béchet, Incremental parsing of Lambek calculus using proof-net interfaces. Pierre Boullier, Guided Earley Parsing. Anna Corazza, Parsing Strategies for the Integration of Two Stochastic Context-Free Grammars. James Henderson, Generative Versus Discriminative Models for Statistical Left-Corner Parsing. Mark-Jan Nederhof, Giorgio Satta, Probabilistic Parsing as Intersection. Khalil Sima'an, On Maximizing Metrics for Syntactic Disambiguation. Hiroyasu Yamada, Yuji Matsumoto, Statistical Dependency Analysis with Support Vector Machines. Gennaro Costagliola, Vincenzo Deufemia, Visual Language Editors based on LR Parsing Techniques. Kenji Sagae, Alon Lavie, Combining Rule-based and Data-driven Techniques for Grammatical Relation Extraction in Spoken Language. Frederik Fouvry, Constraint relaxation with weighted feature structures. Chad Langley, Alon Lavie, Parsing Domain Actions with Phrase-Level Grammars and Memory-Based Learners. Mark-Jan Nederhof, Giorgio Satta, Stuart M. Shieber, Partially Ordered Multiset Context-Free Grammars and ID/LP Parsing. Joakim Nivre, An Efficient Algorithm for Projective Dependency Parsing. Kilian Foth, Wolfgang Menzel, Subtree Parsing to Speed up Deep Analysis. Accepted Poster Presentations ----------------------------- Philippe Blache, Meta-level constraints for representing interaction between linguistic domains. Vladimir Kadlec, Pavel Smrz, PACE --- Parser Comparison and Evaluation. Mi-Young Kim, Jong-Hyeok Lee, S_clause Segmentation for Efficient Syntactic Analysis in Long Sentences. Yong-Jae Kwak So-Young Park Hoojung-Chung Young-Sook Hwang Hae-Chang Rim, GLR Parser with Conditional Action Model using Surface Phrasal Types For Korean. Souha Hammami Mezghani, Chafik Aloulou, Lamia Hadrich Belguith, Ahmed Hadj Kacem, Implémentation du système MASPAR selon une approche multi-agent. Sanghamitra Mohanty, Rakesh Chandra Balabantaray, Intelligent Parsing in Natural Language Processing. [canceled] So-Young Park Yong-Jae Kwak Hoo-Jung Chung Young-Sook Hwang Hae-Chang Rim, Automatic Acquisition of Constraints for Efficient Korean Parsing. Tomasz Obrebski, Dependency parsing using dependency graph for storing alternative structures. For more details, see the Programme page at http://iwpt03.loria.fr/ Registration: ------------- Early registration is possible until March 28; after that date the registration fee will be higher. Please register online using the IWPT'03 web pages at http://iwpt03.loria.fr/ At the web site you can also find information about accomodation and other relevant information. IWPT'03 Organization: --------------------- General Chair: Harry Bunt (Tilburg University, Netherlands) Programme Chair: Gertjan van Noord (University of Groningen, Netherlands) Local Organization Chair: Guy Perrier (LORIA, Nancy, France) Further information ------------------- Additional information about IWPT'03 is available at the URL: http://iwpt03.loria.fr/ At the SIGPARSE site at http://parlevink.cs.utwente.nl/sigparse/ information is available about previous IWPTs, proceedings, books based on IWPTs, and SIGPARSE related activities. ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrainée par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adhésion : http://www.atala.org/ ------------------------------------------------------------------------- From thierry.hamon at LIPN.UNIV-PARIS13.FR Thu Apr 10 09:15:22 2003 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Thu, 10 Apr 2003 11:15:22 +0200 Subject: Appel: ELSNET/ENABLER Resources Infrastructure Workshop at ACL2003 Message-ID: From: Steven Krauwer Message-ID: <20030409170511.A15232 at syntax.let.uu.nl> X-url: http://www.elsnet.org/acl2003-workshop X-url: http://www.elsnet.org ACL2003 Resources Information Infrastructure Workshop _________________________________________________________________ Last CALL for PAPERS Towards a Resources Information Infrastructure Workshop at ACL2003 in Sapporo (Japan) July 11 and 12 2003 Organised by ENABLER / ELSNET Description The problem addressed by this workshop is the well-known information problem. People are creating, exploring and exploiting language resources all over the world. Those who are working with resources know a lot about their own and other resources, and they are generally prepared to share this knowledge, their expertise and in many cases even their resources with others via publications in journals, presentations at conferences, and via the web. Unfortunately this information, however public, is not accessible in any systematic way for those who need resources, who want to know what sort of resources exist, how resources should be annotated, which standards to adhere to, which tools to use, etc etc. We will call this problem the 'Resources Information Problem'. The problem has also a geographical dimension: As work on specific languages is very often concentrated in specific parts of the world, much relevant information has a tendency to stay in one geographical place. This is an obstacle for those who are working on these same languages in different parts of the world, and it makes it harder to port knowledge and expertise gained on one language to other languages. The above observation are far from novel, and it would be naive to think that the problems will ever go away. At the same time one can observe that there are organisations (associations, agencies, projects, networks, etc) that have access to parts or fragments of this information and that have their own infrastructures that facilitate access to this information by internal or external people. The purpose of this workshop is to investigate how we can exploit the existing infrastructures to a maximum in order to facilitate world-wide access to information on language resources. The role of the workshop will be to bootstrap this process. Approach * First of all we will try to make an initial map of the language resources landscape world-wide. This map will include actors, organisations, repositories, standards, projects, tool libraries, etc etc. All participants will be asked beforehand to submit pointers to such items. They will be collected and published. * At the workshop we will invite representatives of a number of organisations that can be seen as key actors in the field, and they will be asked to present ideas about the way their organisation could contribute to solving the Resources Information Problem. These ideas could range from very concrete and immediately implementable proposals to longer term and visionary actions. * A round table discussion at the workshop will aim at the creation of convergence, coherence and synergies between the proposed actions. The intended output is a catalogue of actions to facilitate access to resources information that could be implemented (almost) immediately, a skeleton plan for longer term actions, and firm commitment from key players to make these things happen. Target audience Representatives of parties that could play a key role in providing access to resources information, such as (but not limited to) * Resources distribution agencies, e.g. LDC and ELDA/ELRA * Professional organisations, e.g. ACL, ISCA, and their regional branches, e.g. EACL, AACL, JACL, Asian NLP federation * Networks and resources infrastructure projects, e.g. ENABLER, ISLE. ELSNET * Committees, e.g. ICWLR, COCOSDA * National resources or infrastructure projects, e.g. Technolangue, Collate * International actions, e.g. OLAC * Researchers and developers interested in improving the language resources infrastructure for our community Invited and submitted papers We expect to invite some 15 representatives to give their presentations, but in addition we are issuing an open call for papers addressing the resources information problem and possible solutions. These papers will be reviewed in the usual way. Submission format Please submit full papers of maximum 8 pages (including references, figures etc). Authors should follow the main conference ACL style format. Electronic submission only. Send the pdf, postscript, or MS Word form of your submission to: Steven Krauwer (steven.krauwer at elsnet.org) who will also answer any queries regarding the submission. Important Dates Submission deadline for workshop papers: 13 April 2003 Notification of accepted papers: 14 May 2003 Deadline for camera ready copies 29 May 2003 Workshop dates: 11-12 July 2003 Workshop Format It will be a two-day workshop, with invited and submitted presentations in the mornings, and topical panels and round table discussion in the afternoons, including an open meeting of the newly created International Coordination Committee for Written Language Resources. Programme Committee As this workshop is jointly organized by ELSNET and ENABLER (two EU funded projects aimed at providing collaboration infrastructures), we have invited all ca 60 members of the ELSNET and ENABLER Boards to constitute the core programme committee. We may want to invite additional members from Asia and other parts of the world in order to ensure sufficient geographical coverage. A full list of PC members will be published on the workshop website at http://www.elsnet.org/acl2003-workshop The workshop will be jointly chaired by Steven Krauwer (ELSNET) and Nicoletta Calzolari/Antonio Zampolli (ENABLER) Historical note This workshop can be seen as a follow-up of the workshop organised at ACL2000 in Hong Kong, entitled 'Towards infrastructures for global collaboration'. One of the conclusions of this workshop was that the field of language resources would offer good opportunities for collaborative actions, and the first concrete goal was the creation of an international resources federation, a first step towards which is now embodied by the proposal to set up an International Committee for Written Language Resources. The workshop should lead to the definition of concrete actions to be carried out under the auspices of ICWLR, in collaboration with other organisations. Contact info Steven Krauwer (steven.krauwer at elsnet.org), ELSNET (http://www.elsnet.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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain�e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh�sion : http://www.atala.org/ ------------------------------------------------------------------------- From thierry.hamon at LIPN.UNIV-PARIS13.FR Thu Apr 10 09:15:23 2003 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Thu, 10 Apr 2003 11:15:23 +0200 Subject: Appel: GL2003 (Deuxieme Appel) Message-ID: From: Pierrette Bouillon Message-id: <3E952B19.3020501 at issco.unige.ch> X-url: http://issco-www.unige.ch/ X-url: http://issco-www.unige.ch/gl2003.html ============================================================================ 2nd International Workshop on Generative Approaches to the Lexicon (Endorsed by ACL SIGLEX) ============================================================================ Second call for participation May 15-17, 2003 School of Translation and Interpretation, University of Geneva (Switzerland) http://issco-www.unige.ch/gl2003.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 In this second workshop we would like to keep all the above perspectives, but put more of the focus on available on-line lexical resources in order to compare experience. The discussions will be centered, but not limited to, the following topics: * Building new resources * Acquiring lexical information * Maintaining resources * Representing lexical information (i.e. polysemy, collocation links, multiword expressions, predicate-argument structure) * Using lexical information in applications * Specialization and customization for specific applications * Links between different frameworks * Sharing lexical resourcesBuilding Lexical Resources * Multilinguality in the lexicon * Standardization and evaluation The conference will be held over a period of two and a half days. Oral presentations (30 min) and poster presentations are foreseen. Invited speakers include: Nicoletta Calzolari (Istituto Di Linguistica Computazionale, Pisa) Ann Copestake (Cambridge University, Cambridge) Christiane Fellbaum (Princeton University) Charles J. Fillmore(International Computer Science Institute, Berkeley) Alex Lascarides (University of Edinburgh) James Pustejovsky (Brandeis University,Brandeis). GL2003 is: - founded by the Swiss National Science Foundation (FNRS) and the Communications Research Laboratory (Japan) - hosted by University of Geneva, School of Translation and Interpretation, TIM/ISSCO (Switzerland). Organizers: Pierrette Bouillon (School of Translation and Interpretation, TIM/ISSCO, University of Geneva, Switzerland) Kyoko Kanzaki (Communications Research Laboratory, Japan) Program Committee: Susan Armstrong (University of Geneva) Toni Badia (Universitat Pompeu Fabra, Barcelona) Sabine Bergler (Concordia University, Montreal) Federica Busa (MIT, Sloan school of Management) Nicoletta Calzolari (Istituto Di Linguistica Computazionale, Pisa) Ann Copestake (University of Cambridge, Cambridge) Laurence Danlos (University of Paris VII, Paris) Pierre Frath (Marc Bloch University, Strasbourg) Charles J. Fillmore (International Computer Science Institute, Berkeley) Sandiway Fong (NEC, Princeton) Thierry Fontenelle (Microsoft, Seattle) Jacques Jayez (EHESS-CELITH, Paris) Hitoshi Isahara (Communications Research Laboratory, Kyoto) Adam Kilgarriff (ITRI, University of Brighton, Brighton) Alex Lascarides (University of Edinburgh, Edinburgh) Andrei Popescu-Belis (ISSCO/TIM, Geneva) James Pustejovsky (Brandeis University, Boston) Pascale Sebillot (Irisa, Rennes) Evelyne Viegas (Microsoft, Seattle) Piek Vossen (Irion Technologies, Delft) The GL2003 program and registration form are now available at: ============================================================================== http://issco-www.unige.ch/gl2003.html ============================================================================== ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain�e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh�sion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Tue Apr 22 08:19:53 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Tue, 22 Apr 2003 10:19:53 +0200 Subject: Appel: Workshop on MT Evaluation Message-ID: Workshop on MT Evaluation Towards Systematizing MT Evaluation Theme: Estimating the quality of any machine-translation system accurately is only possible if the evaluation methodology is robust and systematic. The NSF and EU-funded ISLE project has created a taxonomy that relates situations and measures for a variety of MT applications. The Framework for MT Evaluation in ISLE (FEMTI) is now available online at http://www.issco.unige.ch/projects/isle/taxonomy3/. The effort of matching these measures correctly with their appropriate evaluation tasks, however, is an area that needs further attention. For example, what effect do user needs have on the functionality characteristics specified in the FEMTI guidelines? To what extent are there unseen relationships in the branches of the taxonomy? How can we judge when a given evaluation measure is appropriate? Issues that come to bear on this question are the automation of MT evaluation, the extension to MT applications such as automated speech-translation, and the evaluation of the very training corpora that an MT system relies on to improve output quality. This workshop welcomes papers for 30-minute presentations on the comparison between MT evaluation measures, studies of the behavior of individual measures (i.e., meta-evaluation), new uses for measures, analysis of MT evaluation tasks with respect to measures, and related topics on this theme. We solicit submissions to the workshop that address some of the following issues, however any other topic related to MT Testing and Evaluation is also acceptable: Machine Translation Evaluation Measures: - Use of existing measures in the ISLE hierarchy (FEMTI guidelines) - New measures and their uses - Matching evaluation requirements (e.g., translation tasks, user profiles) with - measures - Effects of combining measures Evaluation Measures and Languages - Is a metrics effectiveness language independent? - Counting grammatical features for evaluation Evaluation and Domains - Measures for spoken Language translation - Domain-specific evaluation techniques - Using measures to evaluate the quality of a training corpus for a given task Automation vs. Human Testing - Which measures are suitable for automation? - Human/machine scoring comparisons - Human tester agreement: which measures fare best? -------------------------------------------------------------------------------- Submission Format Papers (full papers up to 8 pages in length) must be submitted electronically to: barrett at semanticdatasystems.com , or andrei.popescu-belis at issco.unige.ch Papers are preferred in .pdf, .ps, .rtf, or .txt, format -------------------------------------------------------------------------------- Important Dates: Paper submission deadline: May 11 Notification: June 30 Camera-ready due: July 31 Note: the workshop will be held on September 23, 2003 -------------------------------------------------------------------------------- Also see workshop website for updates: http://www.issco.unige.ch/projects/isle/MTE-at-MTS9.html -------------------------------------------------------------------------------- Contacts Leslie Barrett (Transclick, Inc., New York, NY) Andrei Popescu-Belis (ISSCO/TIM/ETI, University of Geneva) -------------------------------------------------------------------------------- Organizers Leslie Barrett (Transclick, Inc., New York, NY) Maghi King (ISSCO/TIM/ETI, University of Geneva) Keith Miller (MITRE Corp) Andrei Popescu-Belis (ISSCO/TIM/ETI, University of Geneva) -------------------------------------------------------------------------------- Program Committee: Bonnie Dorr (University of Maryland) Eduard Hovy (Information Sciences Institute, University of Southern California) Maghi King (ISSCO/TIM/ETI, University of Geneva) Bente Maegaard (Center for Sprogteknologi, Copenhagen, Denmark) Keith Miller (MITRE Corp.) Martha Palmer (University of Pennsylvania) Ted Petersen (Univesity of Minnesota) Andrei Popescu-Belis (ISSCO/TIM/ETI, University of Geneva) Florence Reeder (MITRE Corp) Nancy Underwood (ISSCO/TIM/ETI, University of Geneva) Michelle Vanni (National Computer Security Center) ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain�e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh�sion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Tue Apr 22 08:19:57 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Tue, 22 Apr 2003 10:19:57 +0200 Subject: Conf: resultats du projet Euromap Message-ID: ******************************************************************************** Progres des technologies de la langue en Europe, la position de la France ******************************************************************************** Apres le succes de son premier seminaire, qui a eu lieu en juillet 2002 et à l'occasion de la fin du projet Euromap, ELDA organise un deuxieme evenement, dedie aux technologies de la langue, qui aura lieu le lundi 28 avril 2003 au 17, rue Hamelin Paris 16eme (Metro Boissiere ou Iena), de 14h à 17h30. Ce seminaire sera suivi d'un cocktail gracieusement offert par Euromap France. Ce seminaire portera d'une part sur les resultats du projet Euromap, qui couvrent l'etat des lieux en technologies de la langue en Europe, aussi bien de facon qualificative que quantitative, avec une analyse des differentes initiatives nationales. Par ailleurs une presentation de l'evolution de la scene europeenne sera faite avec une description des nouveaux instruments du 6eme Programme cadre de la Commission europeenne, en particulier l'ERA-NET (l'espace europeen de recherche) et son application aux technologies de la langue. D'autre part, les nouvelles initiatives en Evaluation seront introduites par l'equipe d'ELDA. Et enfin, des representants des ministeres initiateurs du programme Technolangue (le Ministere charge de la Recherche et des Nouvelles Technologies, le Ministere delegue a l'Industrie et le Ministere de la Culture et de la Communication) feront etat de l'avancement du programme. Ce seminaire s'adresse aux developpeurs, integrateurs, chercheurs et utilisateurs des technologies de la langue. Renseignements & inscriptions: ***************************** Les inscriptions sont obligatoires et se font par courrier electronique à Mahtab Nikkhou, nikkhou at elda.fr, en indiquant votre nom, fonction et vos coordonnees professionnelles, jusqu'au 24 avril 2003 au soir. L'entree au seminaire est gratuite. Programme: ***************** Progres des technologies de la langue en Europe, la position de la France 14h00 Accueil 14h15 Euromap Technologies de la Langue : bilan du projet, presentation du rapport final, analyse comparative des technologies de la langue en France et en Europe Bente Maegaard, Andrew Joscelyne (Euromap) 15h00 Programme Technolangue, avancements et nouvelles orientations Joseph Mariani, Stephane Chaudiron, Jacques Mathieu (Ministere en charge de la Recherche et des Nouvelles Technologies, MINEFI ) 15h45 Activite d'evaluation au sein d'ELDA, projet Evalda- Khalid Choukri 16h15 ERA-NET, Espace europeen de recherche en technologies de la langue, 6eme PCRDT (Commission europeenne) 17h00 Foire aux questions 17h30 Fin du seminaire, Cocktail offert par Euromap France Ce seminaire est organise dans le cadre du projet communautaire "Euromap-Technologies de la Langue". **Euromap** Lance par la Commission europeenne, Euromap Technologie de la Langue est un projet de collecte et de dissemination d'informations, visant a faire la promotion et la cartographie de l'ingenierie linguistique en Europe. Depuis le mois d'octobre 2001, ELDA participe a ce projet en tant que representant de la France, en partenariat avec dix autres pays europeens. Pour en savoir plus cliquez sur http://www.elda.fr/fr/proj/euromap.html (site francais) et http://www.hltcentral.org/euromap (site central). **Technolangue** C'est une action interministerielle destinee a mettre en place de maniere perenne une infrastructure de production et diffusion de ressources linguistiques, d'evaluation des technologies de la langue ecrite et orale, de participation aux instances nationales et internationales de normalisation et de standardisation et de veille informationnelle sur le domaine. Les ministeres concernes sont le Ministere charge de la Recherche et des Nouvelles Technologies, le Ministere delegue a l'Industrie et le Ministere de la Culture et de la Communication. **6eme PCRDT/programme-cadre de R&D IST 2002-2006** Le nouveau programme-cadre communautaire pour des actions de recherche et de developpement technologique presente des changements importants dans le financement de la recherche, en particulier avec les nouveaux instruments que sont les projets integres, les reseaux d'excellence et les possibilites d'une meilleure coordination et integration avec les programmes nationaux. *** ELDA - Agence pour la distribution des ressources linguistiques et l'evaluation *** Creee en 1995, L'Agence pour la distribution des ressources linguistiques et l'evaluation (Evaluation and Language resources Distribution Agency) a pour mission l'identification, la collecte et la promotion de ressources linguistiques dans le but de les rendre disponibles aupres des developpeurs et utilisateurs de systemes lies au traitement de la langue. ELDA est egalement partie prenante de projets d'evaluation (de systemes, outils, applications, etc.), s'occupe de la diffusion de l'information relative au domaine de l'ingenierie linguistique et participe a de nombreux projets francais, europeens et internationaux. Pour en savoir plus cliquez sur: http://www.elda.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://listserv.linguistlist.org/archives/ln.html La liste LN est parrainée par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adhésion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Tue Apr 22 08:20:01 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Tue, 22 Apr 2003 10:20:01 +0200 Subject: Appel: EUROLAN'03 : Ontologies and Information Extraction Message-ID: We appologies for multiple posting ===================================== Ontologies and Information Extraction International Workshop held as part of the EUROLAN'03 Summer School July 28 - August 8, 2003 Bucarest, Romania New extended dead-line: 5th May 2003 Call for Papers Information Extraction systems were designed to filter, to select and to classify the increasing amount of information available nowadays, mainly on the Web. Most of them were based on shallow natural language processing techniques, but semantics was not really used, due to the unavailability of generic ontologies. During last years, some generic ontologies become available and a lot of research projets tried to take into account semantic aspects to obtain more precise results for IE systems. Meanwhile, important efforts concentrate on developping tools for semi- automatic building of domain-specific ontologies, based on IE and text- mining techniques. This workshop will provide a forum for discussion between leading names in the field and researchers involved in the development of ontology-based IE systems or semi-automatic tools for building ontologies. We would like to invite researchers, master and Ph.D. students to submit their original and unpublished work to the workshop. Topics of interest include but are not limited to: - semantic annotation; - content-based indexing and retrieval; - robust analysis of language data; - text mining; - platforms for semi-automatic ontology extraction; - formalisms for ontology representations. Submission Requirements Authors are invited to submit a 4-6 pages extended abstract in electronic form (postscript or PDF) by 05th May 2003. Authors of accepted papers should submit the final version in electronic format not later than 15th of June. The documents must be in either postscript or pdf format (PDF is encouraged, but postscript documents are acceptable as well). If you have problems delivering your paper in one of these formats, please contact the organising comittee. Maximum length of paper should be about 10 pages. This workshop uses the same guidelines as EACL-2003. The instructions can be found at http://ic.epfl.ch/~pallotta/ontoIE/. Please do not insert page numbers, headers or footers. If you have any problem following the style please contact the organising committee as soon as possible. All the papers should be send to Amalia.Todirascu at utt.fr =============================================================== Important Dates Submission Deadline: 05th May 2003 Notification of Acceptance: 20th May 2003 Camera-ready Papers: 15th June 2003 Demos of working or under development systems are encouraged. ==================================== Registration People wanting to attend the workshop must be registered at the Eurolan'03 School. Participation to the workshop is open to all Eurolan'03 attendants. Copies of workshop proceedings will be made available. Authors of the papers accepted for presentation at the workshop will benefit of early registration fee no matter the date they register. ==================================== Programme Commitee Nathalie Aussenac-Gilles (IRIT, Toulouse, France) Roberto Basili (University of Rome 2 "Tor Vergata", Italy) Bill Black (UMIST, Manchester, UK) Paul Buitelaar (DFKI, Saarbrucken, Germany) Amedeo Cappelli (University of Pisa, Italy) Paola Merlo (University of Geneva, Switzerland) Malvina Nissim (University of Edinburgh, Scotland, UK) Fabio Rinaldi (University of Zurich, Switzerland) Laurent Romary (LORIA, Nancy, France) Patrick Ruch (EPFL, Lausanne, Switzerland) Horacio Saggion (University of Sheffield, UK) Manuela Speranza (IRST, Trento) Steffen Staab (AISB, University of Karlsruhe, Germany) Valentin Tablan (University of Sheffield, UK) Dan Tufis (Romanian Academy, Bucharest, Romania) Organising commitee Amalia Todirascu (Technological University of Troyes, France) Vincenzo Pallotta (EPFL, Lausanne, Switzerland) ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain�e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh�sion : http://www.atala.org/ ------------------------------------------------------------------------- From thierry.hamon at LIPN.UNIV-PARIS13.FR Thu Apr 24 15:39:58 2003 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Thu, 24 Apr 2003 17:39:58 +0200 Subject: Q: Travaux sur les analyseurs syntaxiques et l'approche multi-agent Message-ID: Date: Fri, 11 Apr 2003 17:47:02 +0200 From: "souha.mezghani at laposte.net" Message-Id: Salut tout le monde, Est ce que vous pouvez me referencier sur des travaux utilisant l'approche multi-agent pour la realisation d'un analyseur syntaxique. merci, Souha ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain�e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh�sion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Fri Apr 25 08:04:50 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Fri, 25 Apr 2003 10:04:50 +0200 Subject: Jobs: U. of Groningen : Prof. of Romance Linguistics Message-ID: University of Groningen Faculty of Arts The post is within the Department of Romance Languages and Cultures. The Faculty of Arts of the University of Groningen has a vacancy for the post of Professor of Romance Linguistics. This chair has been created within the Faculty fast-track regulation and, therefore, the current professor and his successor will operate in tandem until 1 January 2005. The aim of the Faculty fast-track regulation is to enable young talent to join or move through the system faster. Candidates may not be older than 45 years of age - that is, they may not have turned 46 on 1 January of the year following their appointment. Professor of Romance Linguistics VACANCY NUMBER 203122/2731 The discipline covers Romance linguistics in the widest possible sense. The professor will be responsible for and must contribute to the teaching and the research within the scope of the department. The professor appointed should preferably work in the field of Romance Linguistics but must be experienced in the field of French Linguistics. He or she must be a specialist in one or more of the approaches to linguistics. The position co-ordinating and providing teaching in the field of Romance Linguistics co-ordinating and performing research in the field of Romance Linguistics supervising PhD candidates performing administrative and organisational duties deepening and promoting the national and international contacts of the department. Profile We are looking for candidates who will provide enthusiastic leadership to a team which keeps a close watch on the newest developments in the fields of teaching, politics and culture. Interested parties must fulfil the following conditions: be no older than 45 years of age (see above) have a PhD in the field of Romance Linguistics be an experienced lecturer with extensive research experience in the field of Romance Linguistics, with specific expertise in the field of French Linguistics. have good administrative and organisational skills be able to promote interest in the field be prepared to move to the Groningen area. Post The RUG is offering a full-time appointment as Full Professor (A) from 1 September 2003. The salary will be EUR 4,428 - EUR 6,462 per month gross (Collective Labour Agreement (CAO) for Dutch Universities). Information Please contact Prof. G.J. de Haan, dean of the Faculty, tel. +31 (0)50 363 5900, e-mail: g.j.de.haan at let.rug.nl if you would like more information. You can request an information package from the secretary of the Faculty of Arts, Ms. G. Peters-Beuke, tel. +31 (0)50 363 5900. If you would like to draw our attention to suitably qualified candidates, please write to the director of the Department of Personnel and Organisation within two weeks. The closing date for applications is 4.6.2003 Please send your written application and curriculum vitae to: The University of Groningen, Personnel & Organisation Department P.O. Box 72, 9700 AB Groningen, The Netherlands. Please state the vacancy number on the envelope and at the top of your letter. There are a number of interesting vacancies at the RUG. Additional information about vacancies at the RUG is available on the university web site: www.rug.nl The RUG has a special careers advisory service for the partners of new staff who move to the area. The RUG is an equal opportunities employer. Because women are still underrepresented in a number of fields, they are particularly encouraged to apply. University Hospital Groningen, Municipality of Groningen, Hanzehogeschool, Informatie Beheer Groep, Martini Hospital, N.V. Nederlandse Gasunie, province of Groningen, University of Groningen and Groningen Regional Police Force are all members of the Noorderlink co-operation (www.noorderlink.nl). If you work for one of these organisations, please write INTERN at the top of your letter. ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrainée par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adhésion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Fri Apr 25 08:04:53 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Fri, 25 Apr 2003 10:04:53 +0200 Subject: ATALA: JOURNEE du 17/05 : EXTENSION DE DATE LIMITE DE SOUMISSION Message-ID: [English version below] EXTENSION DE DATE LIMITE DE SOUMISSION ---------------------------------------------------- JOURNEES de l'ATALA - APPEL A COMMUNICATION Des requêtes aux questions : nouvelle perspective pour la recherche d'information ? >From queries to questions: new perspective for information retrieval? Date limite de soumission prolongée au 28 avril - English version below ------------------------------------------- Samedi 17 mai 2003 ENST, rue Barrault, Paris 13eme Organisée par Brigitte Grau (LIMSI) et Olivier Ferret (CEA-LIST) Face à une question telle que «Quelle est la voiture la plus chère du monde ?», les moteurs de recherche traditionnels renvoient l?ensemble des documents les plus fortement liés aux mots de la question, en sélectionnant éventuellement un passage, mais laissent à la charge de l?utilisateur la tâche d?explorer ces documents afin d?y trouver la réponse. L?introduction de la tâche «Question Answering» lors de l?évaluation TREC8 (Text REtrieval Conference), en 1999, est révélatrice du besoin sans cesse croissant de disposer de systèmes de recherche d?information allant au delà de la simple recherche documentaire habituellement proposée. Cette pression a conduit au développement de systèmes capables d?extraire les parties des documents les plus pertinentes par rapport à une question posée, en proposant directement une réponse lorsqu?il s?agit d?une question factuelle ou un résumé si la requête est de nature thématique. Les systèmes développés dans le cadre des évaluations TREC de ces dernières années représentent un premier stade dans la problématique d?une recherche d?information axée sur la notion de question/réponse. Cette problématique, esquissée dans un roadmap récent (cf. http://www-nlpir.nist.gov/projects/duc/roadmapping.html), met en avant des fonctionnalités nouvelles ou encore assez embryonnaires dans les systèmes de recherche d?information actuels: évaluation de l?existence d?une réponse à une question dans une base de textes, synthèse de réponses multiples intra ou inter-documents, dialogue d?aide à la formulation de requête ou encore capacités de compréhension de texte permettant par exemple de reconnaître des reprises anaphoriques ou de juger de l?éventuelle incompatibilité de réponses multiples. Ces nouvelles fonctionnalités imposent aux systèmes de recherche d?information de mener une analyse plus en profondeur à la fois des requêtes qui leur sont adressées et des documents au sein desquels ils doivent chercher les informations permettant d?y répondre. C?est pourquoi la problématique des systèmes de question/réponse se situe à l?intersection de plusieurs domaines: elle possède bien entendu un ancrage originel fort dans le domaine de la recherche d?information mais elle fait aussi appel de façon importante au traitement automatique des langues (TAL) ainsi que plus ponctuellement à des domaines tels que l?apprentissage automatique. Typiquement, un système de question/réponse s?articule ainsi autour d?un moteur de recherche traditionnel, enrichi en amont par un module d?analyse des questions et en aval par des modules robustes d?analyse des documents assurant l?extraction de passages réponses en mêlant l?exploitation de traits linguistiques, aussi bien de nature morphologique, syntaxique ou sémantique, et l?utilisation de critères numériques, plus classiques en recherche d?information. De ces spécificités se dégagent plusieurs axes fort de la problématique question/réponse telle qu?elle est envisagée actuellement. Le premier de ces axes est le fait que l?analyse des requêtes est considérée comme une fonction importante visant à déterminer les intentions de l?utilisateur, soit le but de sa recherche, et non plus seulement à produire un ensemble de mots-clés. L?impact de cette analyse sur les résultats de la recherche a bien entendu pour objectif d?inciter les utilisateurs à formuler leurs requêtes sous une forme suffisamment riche, en l?occurrence des questions en langue naturelle, pour permettre la mise en évidence de l?objet de leur recherche. Le second axe concerne la nécessaire robustesse des modules linguistiques d?analyse des documents. Le problème des systèmes de question/réponse a été exploré dès les premiers travaux en TAL (Lehnert 1977) mais sur des domaines limités seulement. Actuellement, même si le cas de figure des domaines fermés demeure, comme avec les FAQ (Frequently Asked Questions), l?intérêt se porte majoritairement sur des systèmes de question/réponse en domaine ouvert répondant à des questions de nature factuelle ou encyclopédique à partir de très grosses base de textes, voire du WEB. Dans ce cadre, il n?est pas possible de poser de restrictions a priori tant pour ce qui est des domaines abordés que des types de textes traités. Il s?agit là d?un enjeu important pour le TAL auquel peut contribuer de façon significative l?apprentissage automatique. Un dernier axe de cette nouvelle problématique de la recherche d?information, en relation étroite avec le précédent, concerne la capacité des systèmes à auto-évaluer leurs résultats et à utiliser différents niveaux de traitement. Être confronté à des documents sans possibilité de contrôle quant à leur nature ou leur sujet signifie que les modules d?analyse des documents les plus sophistiqués, donc les plus fragiles, sont parfois mis en défaut et produisent des résultats moins pertinents que ceux issus de modules moins élaborés mais plus robustes. La capacité à déterminer lorsqu?un tel cas de figure se produit et à le gérer est sans doute une des clés du succès de l?utilisation du TAL en recherche d?information. Son impact sur l?architecture des systèmes développés est particulièrement important. Alors qu?une évaluation des systèmes de question/réponse en Français est en cours de préparation dans le cadre du récent appel Technolangue des ministères de la Recherche et l?Industrie, l?objectif de cette journée de l?ATALA est de faire le point sur l?état actuel des recherches concernant la problématique question/réponse et de présenter les travaux déjà réalisés dans ce domaine, en particulier dans la sphère francophone, ou les travaux y contribuant directement. Plus spécifiquement, les propositions de communication pourront présenter des systèmes de question/réponse dans leur ensemble ou bien des traitements constitutifs de tels systèmes pourvu qu?ils soient replacés dans la problématique question/réponse. Parmi ces traitements, on peut notamment citer: - analyse de questions: typologie de questions, extraction de l?objet de la question, de son contexte, de contraintes sémantiques - reconnaissance d?entités nommées:en domaine ouvert, typage fin - extraction de passages - similarité de représentations syntaxiques, partielles ou complètes - outils terminologiques: extraction et reconnaissance de termes et de leurs variantes - appariement question - passage de texte fondés sur des traits linguistiques: traits morphologiques, syntaxiques ou sémantiques - extraction et justification des réponses: patrons de réponse, inférences, paraphrase ? La cible privilégiée de cette journée est constituée par des travaux portant sur des bases textuelles importantes ou à partir du WEB mais les systèmes de question/réponse destinés à des domaines restreints ou couplés à des bases de connaissances ou des bases de données peuvent également être concernés dans la mesure où certains traitements, tels que l?analyse de questions par exemple, sont similaires. Les propositions de communication pourront également aborder des thèmes plus transversaux en relation avec les systèmes de question/réponse, thèmes parmi lesquels: - l?apprentissage automatique; que ce soit pour acquérir sur une large échelle des ressources utilisables par un système de question/réponse ou plus directement, pour apprendre à sélectionner et extraire la réponse à une question; - le multilinguisme: difficulté de passer d?une langue à une autre, sachant que la plupart des systèmes ont été développés pour l?anglais; possibilité de poser une question dans une langue et de chercher la réponse dans des documents écrits dans une autre langue; - le WEB: utilisation du WEB en tant que source de connaissances ou de réponses; spécificité de la recherche de réponses sur le WEB; - le multi-document: fusion et cohérence de réponses multiples. Nous demandons aux auteurs de préciser si leur soumission : 1) concerne des travaux en cours, ou des prises de position; 2) des travaux aboutis du point de vue théorique ou appliqué. Soumission (modalités) Un résumé de 2 à 3 pages doit être envoyé avant le 28 avril 2003 par courrier électronique en format text, .rtf, .doc ou .pdf à : Brigitte Grau : Brigitte.Grau at limsi.fr et Olivier Ferret: olivier.ferret at cea.fr Les notifications d'acceptation seront données pour le 5 mai 2003. ---------------------------------------------------------------------- >From queries to questions: new perspective for information retrieval? Facing a question such as «What is the most expensive car in the world?», classical search engines return the documents that are the most strongly linked to the words of the question, sometimes extract the excerpts where these words are the most numerous, but let the user browse texts to actually find an answer. The creation of the Question Answering (QA) task in the TREC8 evaluation (Text REtrieval Conference) in 1999 is the expression of the increasing need to make information retrieval (IR) systems go further than document retrieval. This need leads to develop systems that are able to extract the parts of documents that are the most relevant in relation to a question, providing either an answer when the question is about a precise fact or a summary when it is a topical question. The systems built for the TREC QA evaluations represent a first stage in a more global view of Information Retrieval that is centered on question answering. This perspective, which is presented in a recent roadmap document (see http://www-nlpir.nist.gov/projects/duc/roadmapping.html), puts forward new functions or functions that are still in an embryonic state in current IR systems: evaluating if an answer to a question exists in a large document collection, using dialog for building a query or text understanding capabilities for dealing with anaphora or determining if several answers are coherent. These new functions can be implemented only if IR systems are able to analyze both queries and documents more deeply. As a consequence, question answering is at the crossing of several research fields: of course, it is grounded in Information Retrieval but it also concerns Natural Language Processing (NLP) in an important way and to some extent, fields such as Machine Learning. Most QA systems are based on a classical search engine that is enhanced by a question analysis module, a set of modules for extracting various linguistic features from documents, such as named entities, terms or syntactic relations, and a module that relies on all these data for extracting answers by mixing linguistic and numerical criteria. Tackling question answering in this way brings to the fore a set of issues that renew the Information Retrieval field. The first of these issues is the fact that in the question answering context, a request is not just a bag of words. Its analysis is an important function that aims at finding user?s intentions, i.e. the goal of its search. Performing such an analysis must have an influence on results in such a way that it leads users to express their requests by the means of true questions. A second issue raised by question answering is the need for robustness for the linguistic modules that analyze documents. The question answering problem was already investigated by some early work in the NLP field (Lehnert 1977) but only in restricted domains. At the moment, even if performing question answering in a restricted domain, for instance to query FAQ (Frequently Asked Questions), is still interesting, the main interest focuses on open-domain QA systems that answer to factoïd questions from very large collections of documents or from the WEB. In these two cases, it is not possible to set a priori restrictions about the type of the documents or their topics. As a consequence, robustness is an important issue for the use of NLP in Information Retrieval and Machine Learning can significantly contribute to it. The last aspect of this new viewpoint on information retrieval, closely linked to the previous one, is the capability for a system to auto-evaluate its results and to deal with incomplete results. When the type and the topic of the documents that are processed are not restricted, the most sophisticated modules that analyze them, which are also the most brittle ones, sometimes fail or provide worst results than rougher but more robust modules. The ability to determine when such a case happens and then to manage it is certainly one of the key for a successful use of NLP in Information Retrieval. Its impact on the design of question answering systems is particularly important. While an evaluation of question answering systems for French is beginning in the context of the Technolangue project, from the French ministry of Research and the French ministry of Industry, the aim of this ATALA workshop is to give an overview of the work done in a question answering perspective, especially in the Francophone community. More precisely, submissions will present a question answering system as a whole or will focus on one of its processes provided that it is put in the question answering context. These processes include but are not limited to: - question analysis: question typology, extraction of the question focus, of the question context or more generally, of semantic constraints - named entity recognition: fine-grained named entities, unrestricted domains - passage extraction - full or partial similarity of syntactic structures - terminological tools: extraction et recognition of terms and their variants - text excerpt question matching based on linguistic features: morphological, syntactic or semantic features - extraction and justification of answers: answer patterns, inferences, paraphrase ? This workshop is particularly concerned by papers that focus on QA systems for large collections of documents or the WEB but papers about QA systems for restricted domains or dedicated to knowledge bases or database will also be taken into account as some problems, as question analysis for instance, are shared by the two kinds of systems. Submissions can also tackle cross-domain topics in relation to Question Answering , such as: - QA and machine learning: use of machine learning for selecting and extracting answers to a question but also for building on a large scale resources that are necessary for QA systems; - multilingual and crosslingual QA: what are the difficulties for adapting an existing QA system most of them only work for English to another language; asking a question in a language and searching an answer in a collection of documents in another language; - QA and the WEB: using the WEB as a source of knowledge or a source of answers; what are the specific aspects of searching an answer on the WEB; - multi-document QA: fusion and coherence of multiple answers. Submission: a 2-3 page summary. We ask authors to indicate if their submission: - present in-progress work or is a position paper; - present theoritical or applied completed work. A 2-3-page summary must be sent before April 28, 2003 by e-mail in text, .rtf, .doc or .pdf to: Brigitte Grau : Brigitte.Grau at limsi.fr and Olivier Ferret: olivier.ferret at cea.fr Acceptance notifications will be sent for 5 May 2003. ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrainée par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adhésion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Tue Apr 29 16:39:38 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Tue, 29 Apr 2003 18:39:38 +0200 Subject: Conf: 11th ELSNET Summer School on Language and Speech Communication Message-ID: SECOND ANNOUNCEMENT and CALL for PARTICIPATION The 11th ELSNET Summer School on Language and Speech Communication Topic: Language and Speech Technology in Language Learning Lille (France), Monday July 7 - Friday July 18, 2003 Organized by the University of Lille 3 We are happy to announce that registration for the 11th ELSNET Summer School is now open. For this school we have chosen a topic of great relevance to researchers and developers in Europe and in other multilingual environments: the use of language and speech technology in language learning, both of spoken and of written language. The goal of this workshop is to get young researchers on a track that will eventually contribute to an important application area. The underlying vision (or dream) is The automatic animated language tutor. + Audience and aims: We see the school as mainly research and development oriented, and hence the primary audience are researchers, developers and integrators who will make our vision happen (rather than teachers who would use it). Both technological and pedagogical aspects will be taken into consideration The aims are: * to make the students familiar with the main principles and problems of language learning/teaching * to make them familiar with current best practice in computer assisted language learning * to make them familiar with the main challenges in computer assisted language learning Participants are expected to have a general computational background and some familiarity with language or speech research and/or processing. After completion of the summer school participants should be able to function in teams aimed at designing or implementing tools, environments or courses for Computer Assisted Language Learning (abbreviated CALL). + Course programme: The provisonal programme is available at http://www.elsnet.org/ess2003/schedule.html The 2-weeks programme comprises the following courses: * Introduction to CALL (Teacher: Jozef Colpaert, [Univ of Antwerp]) * Introduction to natural language processing for CALL (Teacher: Wolfgang Menzel [Univ of Hamburg]) * Introduction to speech processing for CALL (Teacher: Philippe Delcloque [MSEC Manchester]) * Using NLP tools in CALL (hands-on) (Teacher: Wolfgang Menzel [Univ of Hamburg]) * Using Speech tools in CALL (hands-on) (Teacher: Michael McTear [Univ of Ulster]) * CALL design and interfaces (Teacher: Philippe Delcloque [MSEC Manchester]) * Grammatical and morphological error diagnosis (Teacher: Lars Borin [Univ of Gothenburg]) * Systems for pronunciation training (Teacher: Anne-Marie Oster [KTH Stockholm]) * Building a grammatical CALL system (hands-on) (Teacher: Lars Borin [Univ of Gothenburg]) * Building a speech CALL system (hands-on) (Teacher: Michael McTear [Univ of Ulster]) All students attend the same full programme, except for the hands-on sessions, where students can sign up for either NLP or Speech oriented streams. In special student sessions students can present their own work. The presentations will be published on the ELSNET website. Please note that the number of places for this summer school is limited and that early registration is recommended. The working language of the Summer School will be English. + Fees: Category Registration fee (euro) Students 125 Academic staff 250 Commercial organisations 500 ELSNET members are entitled to a 20% discount + Food and accommodation: The cost of accommodation (on campus) will be 20 euro per night Meals will be free. + Registration, grants and other information: For detailed information about registration procedures and deadlines, fees, accommodation, grant possibilities, venue, course and social programme, etc visit the ESS2003 website at http://www.univ-lille3.fr/ESS2003 or send an email to the local organizers at elsnetadmin at univ-lille3.fr A limited number of grants (covering the cost of accommodation) may be available. Details and application forms will be published on the website. For information about the programme visit the ESS2003 website or http://www.elsnet.org/ess2003 or contact the chair of the programme committee, Steven Krauwer (steven.krauwer at elsnet.org) __________________________________________________________________________ Steven Krauwer, ELSNET coordinator, UiL-OTS, Trans 10, 3512 JK Utrecht, NL phone: +31 30 253 6050, fax: +31 30 253 6000, email: s.krauwer at elsnet.org http://www.elsnet.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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain�e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh�sion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Tue Apr 29 16:39:45 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Tue, 29 Apr 2003 18:39:45 +0200 Subject: Appel : SEPLN 2003 Message-ID: ____________Last Call for Proposals_________________________ SEPLN 2003 XIX CONGRESO DE LA SOCIEDAD ESPAÑOLA PARA EL PROCESAMIENTO DEL LENGUAJE NATURAL (SEPLN) (19th Conference of the Spanish Society for Natural Language Processing SEPLN) September 10-12, 2003 Universidad de Alcalá de Henares Alcalá de Henares (Madrid) http://oesi.cervantes.es/sepln Introduction The 19th Conference of the Spanish Society for Natural Language Processing (SEPLN) will take place on September 10-12, 2003 in Alcalá de Henares (Madrid, Spain). As in previous editions, the aim of SEPLN for this Conference is to promote the dissemination of research, development and innovation activities conducted by Spanish and foreign researchers in the field of Natural Language Processing (NLP). The conference will provide a forum for discussion and communication to facilitate an effective exchange of knowledge and scientific materials that are necessary for promoting the publication of relevant work and the establishment of means of collaboration with national and international Institutions that are active in this field. Objectives The main motivation of this conference is to provide the business and scientific communities with an ideal forum for presenting their latest research work and developments in the field of Natural Language Processing, as well as to demonstrate the possibilities offered by these solutions and to know about new projects. Consequently, the 19th SEPLN Conference is a meeting place for presenting results and exchanging ideas concerning the present state of development in this field of knowledge. Furthermore, there is the intention of meeting the goal, achieved in previous editions, of identifying future paths for basic research and foreseen software applications, in order to compare them against the market needs. Finally, the conference intends to be an appropriate forum in helping new professionals to become active members in this field. Topics Researchers and businesses are encouraged to send communications, project abstracts or demonstrations related to any of the following topics: Linguistic, mathematic and psycholinguistic models of language Corpus linguistics Monolingual and multilingual information extraction and retrieval Formalisms and grammars for morphological and syntactical analysis Computational Lexicography Monolingual and multilingual text generation Machine translation Speech synthesis and recognition Semantics, pragmatics and discourse Word sense disambiguation NLP industrial applications Automatic textual content analysis Structure of the Conference The Conference will last three days, with sessions dedicated to presenting papers, ongoing research projects, prototype product demonstrations or products connected with topics addressed in the conference. Scientific activities will be complemented by social and tourist activities, allowing attendants to gain a better understanding about the social and cultural dimensions of Alcalá de Henares. Communications Authors are encouraged to send theoretical or system-related proposals, to be presented at the demonstration sessions, earlier than May 16, 2003. Proposals must meet certain format and style requirements Both the delivery and revision of proposals will be done exclusively in electronic format (PostScript or PDF). Proposals will include a title, the complete names of the authors, their address, telephone, fax and e-mail. Proposals will meet the following requirements (concerning the final version, please check the publication format section): - The proposals will be presented in Spanish or English - Overall maximum length will be 3,500 words - Final versions (after notification of acceptance) will follow the style requirements that are described in the publication format section in the website - The proposals will be anonymously revised. Therefore, the files to be submitted will only include the title remaining the rest of the communication free of any auto-references Authors will submit their proposals through the following web system: https://chair.dlsi.ua.es/sepln03/submit.html Projects and Demos As in previous editions, the organizers encourage participants to give oral presentations of projects and demos. Depending on the estimated number of oral presentations, any session may be reserved to this purpose. Proposals must meet certain format and style requirements for presentations. For oral presentation of projects to be accepted, the following information must be included: - Project title - Funding institution - Participant groups in the project - Name, affiliation, e-mail and phone number of the project director - Abstract (2 pages maximum) - If a demonstration is to be performed, further information must be included, as indicated below For demonstrations to be accepted, the following information is mandatory: - Name, affiliation, e-mail and phone number of the authors - Abstract (2 pages maximum) - Time estimation for the whole presentation This information must be received by June 10, 2003 Publication Format The final version of the article will be sent before June 27, 2003 through a web system: https://chair.dlsi.ua.es/sepln03/submit.html - Documents must not include headers or footings - Maximum length will be 8 pages DIN A4 (210 x 297 mm), included references and figures. - In the case of demonstrations and projects, maximum length will be 2 pages. Articles will be sent in Postscript or PDF format. LaTeX format Authors using LaTeX format may download from the Conference website the following style package zip file: latex_new.zip which contains document and bibliography styles, as well as an example showing existing possibilities. Word format Authors using Microsoft Word or compatible may download from the Conference website the following zip file: word_new.zip which includes a pattern file in RTF format and an example showing existing editing possibilities. Important Dates Dates for submission and notifications of acceptance: - Deadline for submitting abstracts: May 16, 2003 - Notification of acceptance: June 20, 2003 - Deadline for submitting the final version: June 27, 2003 - Deadline for submitting projects and demos: June 10, 2003 Program Committee Chairman: Prof. Maximiliano Saiz Noeda (Universitat dAlacant) Members: Prof. José Gabriel Amores Carredano (Universidad de Sevilla) Prof. Toni Badia i Cardús (Universitat Pompeu Fabra) Prof. Manuel de Buenaga Rodríguez (Universidad Europea de Madrid) Prof.ª Irene Castellón Masalles (Universitat de Barcelona) Prof.ª Arantza Díaz de Ilarraza (Euskal Herriko Unibertsitatea) Prof. Antonio Ferrández Rodríguez (Universitat dAlacant) Prof. Mikel Forcada Zubizarreta (Universitat dAlacant) Prof.ª Ana María García Serrano (Universidad Politécnica de Madrid) Prof. Koldo Gojenola Galletebeitia (Euskal Herriko Unibertsitatea) Prof. Xavier Gómez Guinovart (Universidade de Vigo) Prof. Julio Gonzalo Arroyo (Universidad Nacional de Educación a Distancia) Prof. José Miguel Goñi Menoyo (Universidad Politécnica de Madrid) Prof. Joaquim Llisterri (Universitat Autònoma de Barcelona) Prof. Javier Macías Guarasa (Universidad Politécnica de Madrid) Prof. José B. Mariño Acebal (Universitat Politècnica de Catalunya) Prof.ª M. Antonia Martí Antonín (Universitat de Barcelona) Prof.ª Lidia Ana Moreno Boronat (Universitat Politècnica de Valencia) Prof. Lluis Padró (Universitat Politècnica de Catalunya) Prof. Manuel Palomar Sanz (Universitat dAlacant) Prof. José Manuel Pardo Muñoz (Universidad Politécnica de Madrid) Prof.ª Natividad Prieto Sáez (Universitat Politècnica de Valencia) Prof. Germán Rigau (Universitat Politècnica de Catalunya) Prof. Horacio Rodríguez Hontoria (Universitat Politècnica de Catalunya) Prof. Kepa Sarasola Gabiola (Euskal Herriko Unibertsitatea) Prof. L. Alfonso Ureña López (Universidad de Jaén) Prof.ª Mª Felisa Verdejo Maillo (Universidad Nacional de Educación a Distancia) Prof. Manuel Vilares Ferro (Universidade de Vigo) Organising Committee Chairman: Mr. Jesús Antonio Cid Martínez, Academic Director at Instituto Cervantes Coordinator: Ms. Isabel Bermejo Rubio, Responsible for the Bureau of Spanish in the Information Society OESI at Instituto Cervantes Members: Ms. Eva Mª García García, Technician at OESI, Instituto Cervantes Ms. Raquel Tapias Aparicio, Technician at OESI, Instituto Cervantes Mr. John Michael Urresti Graña, Technician at OESI, Instituto Cervantes Collaborators: Ms. Eva Mª Gómez Gómez, Collaborator at OESI, Instituto Cervantes Ms. Rosario Guijarro Huerta, Collaborator at OESI, Instituto Cervantes Advisors: Ms. Esmeralda de Luis Martínez, Chief at the Department of External and Institutional Relations, Instituto Cervantes Ms. Gloria Gamarra Alonso, Technician at the Department of External and Institutional Relations, Instituto Cervantes Further Information Full information is available at the official website of the Conference: http://oesi.cervantes.es/sepln You may also contact the coordinator at any of the following addresses: Secretary of the 19th SEPLN Conference Conference coordinator: Ms. Isabel Bermejo Rubio Oficina del Español en la Sociedad de la Información C/ Libreros, 23 28801 Alcalá de Henares (Madrid) Spain Tel.: +34 91 888 72 94 Fax: +34 91 888 18 26 E-mail: sepln at cervantes.es Conference website: http://oesi.cervantes.es/sepln ____________________________________________________ Oficina del Español en la Sociedad de la Información C/ Libreros, 23 28801 Alcalá de Henares (Madrid) Tfno.: 91 888 72 94; Fax: 91 888 18 26 informaoesi at cervantes.es http://oesi.cervantes.es ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrainée par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adhésion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Tue Apr 29 16:39:51 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Tue, 29 Apr 2003 18:39:51 +0200 Subject: Soft: Unitex: logiciel de traitement de corpus Message-ID: Bonjour, le laboratoire d'informatique de l'Université de Marne-la-Vallée a mis en ligne un logiciel de traitement de corpus nommé Unitex. Ce système permet d'appliquer sur des textes des dictionnaires électroniques de mots simples et de mots composés. Il est ensuite possible de rechercher des motifs syntaxiques au moyen d'automates ou d'expressions régulières, et de produire des concordances décrivant les contextes des occurrences trouvées. Ce logiciel est librement disponible sous licence GPL à l'adresse http://www-igm.univ-mlv.fr/~unitex Il comprend des ressources pour le français, l'anglais, le grec, le portuguais, le russe et le thaï. Ce système fonctionne sous Windows et Linux. Sébastien Paumier IGM, Université de Marne-la-Vallée ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrainée par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adhésion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Tue Apr 29 16:39:58 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Tue, 29 Apr 2003 18:39:58 +0200 Subject: Conf: SIXTH INTEX WORKSHOP Message-ID: ------------------------------------------- SIXTH INTEX WORKSHOP 28-30 May 2003, Sofia, Bulgaria Bulgarian Association of Computational Linguistics (BACL) http://www.bacl.org/6th_intex_workshop_.html LAboratoire de SEmioLinguistique, Didactique et Informatique (LASELDI) http://laseldi.univ-fcomte.fr/intex ------------------------------------------- ------------------------------------ May 28 ------------------------------------ 14:00 15:30: Max Silberztein, Univ. de Franche-Comte: Tutorial for beginners 15:30 16:00: Coffee break 16:00 17:30: Max Silberztein, Univ. de Franche-Comte: Advanced Tutorial ------------------------------------ May 29 ------------------------------------ 9:00 9:30: Svetla Koeva, Stoyan Mihov (Univ. of Sofia, BACL): Welcome speech. 9:30 10:00: Xavier Blanko, Angels CATENA, Sandrine FUENTES, Autonomous Univ. of Barcelona: Macro or microstructure? Improving the lexical coverage of an electronic dictionary while enriching microstructural information 10:00 10:30: Cvetana Krstev, DuÅ¡ko Vitas, Tomas Erjavec, Josef Stefan, Univ. of Belgrade: Conversion between Intex and MULTEX-East Morphosyntactic Description 10:30 11:00: Coffee break 11:00 11:30: Xavier Lepetit, Univ. de Copenhague: L'importance des schemas de realisation lexicale dans le TAL : le cas de l'expression du mouvement 11:30 12:00: Liborio Dibattista, Univ. di Bari: Usage d'INTEX pour la construction et la verification de territoires lexicaux scientifiques historiquement determines: la langue de la neurologie de Duchenne de Boulogne à J.M. Charcot à Jules Dejerine 12:00 12:30: Jean-Marie Viprey, Univ. de Franche-Comte: DIATAG : convivialite d'etiquetage des ambiguites residuelles ; conception d'outils statistiques de controle 12:30 14:00: Lunch 14:00 14:30: Jorge Baptista, Luis Fahsca, Univ. of Algarve: Mapping, filtering and evaluating impact of ambiguous simple words in Portuguese texts 14:30 15:00: Cristina Mota, Technical Univ. of Lisbon: A renewed Portuguese module for INTEX 4.31 15:00 15:30: Tita Kyriacopoulou, Rania VOSKAKI, Anastasia YANNACOPOULOU, Univ. Aristotle of Thessanoliki: Le module grec d'INTEX : Etat de l'art 15:30 16:00: Coffee break 16:30 17:00: Gordana PavloviÄ?-LažetiÄ?, DuÅ¡ko Vitas, Cvetana Krstev, Univ. of Belgrade: Dictionary of toponyms in Serbian 17:00 17:30: Svetla Koeva, Ivelina Stoyanova, Svetlozara Lesseva, Sofia Univ.: INTEX as an educational subject in the Master's program of Computational Linguistics at Sofia University ------------------------------------ May 30 ------------------------------------ 9:00 9:30: Max Silberztein, Univ. de Franche-Comte: NOOJ: A Cooperative Object Oriented Architecture for NLP 9:30 10:00: Ibtiha Farawi, Univ. de Franche-Comte: Conjugaison des verbes arabes avec INTEX 10:00 10:30: Ting-Au Cheng, City Univ. of Hong-Kong: Les classifieurs temporels en chinois: etude preliminaire 10:30 11:00: Coffee break 11:00 11:30: Francois Rousselot, Univ. de Strasbourg: Une station d'ingenierie linguistique pour la creation de terminologie et d'ontologie 11:30 12:00: Ivan ObradoviÄ?, Ranka StankoviÄ?, Gordana PavloviÄ?-LažetiÄ?, Cvetana Krstev, Univ. of Belgrade: Application of INTEX in refinement and validation of Serbian WordNet 12:00 12:30: Svetla Koeva, Stoyan Mihov, Sofia Univ.: Semantic Relations in INTEX 12:30 14:00: Lunch 14:00 14:30: Gisele Chevalier, Sylvia Kasparian, Univ. de Moncton: Lexique-grammaire evolutif de l'acadien avec INTEX 14:30 15:00: Sun-mee Bae, Univ. de Marne-la-Vallee: Reconnaissance automatique des noms figes du coreen avec INTEX 15:00 15:30: Stavroula Voyatzi, Univ. Aristotle of Thessanoliki: Description par automate des adverbes de date du grec moderne 15:30 16:00: Lucia Di Palo, Univ. di Bari: Une lecon methodologique en histoire de la medecine : l'application du systeme INTEX au texte "Recherches physiologiques sur la vie et la mort" de Xavier Bichat. Un nouveau moyen d'exploitation de la langue medicale du XVIII siecle 16:00 20:00: Excursion ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrainée par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adhésion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Fri Apr 4 16:26:09 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Fri, 4 Apr 2003 18:26:09 +0200 Subject: Appel: revue TAL : Evolutions en analyse syntaxique Message-ID: [English Version follows] ------------------------------------------------------------------------ [Revue t.a.l.] Appel ? soumissions t.a.l. : ?volutions en analyse syntaxique Date limite de soumission : 9 Mai 2003 Num?ro dirig? par ?ric de la Clergerie (INRIA) et Martin Rajman (EPFL) http://www.atala.org/tal/appel-syntaxe.html Contexte : Analyse syntaxique ------------------------------------------------------------------------ L'analyse syntaxique est une composante tr?s importante dans le traitement automatique des langues. Elle continue de poser de nombreux probl?mes que ce soit au niveau des formalismes grammaticaux ou au niveau de la complexit? algorithmique, en particulier pour g?rer les ambigu?t?s. N?anmoins, des progr?s ont eu lieu permettant un emploi plus courant et ? plus grande ?chelle de l'analyse syntaxique dans des applications. L'analyse syntaxique regroupe divers courants qui diff?rent sur les objectifs vis?s et sur les m?thodes employ?es. Les m?thodes couvrent par exemple les approches stochastiques, les approches par cascades (de phases d'analyse locale) et les approches plus traditionnelles d'analyse compl?te (ou profonde). Les objectifs vont de la segmentation en syntagmes ? l'analyse profonde avec une grammaire ? large couverture, en passant par des analyseurs robustes et/ou superficiels. N?anmoins cette diversit? dans les m?thodes et objectifs refl?te une certaine compl?mentarit? plut?t qu'une opposition absolue. Le foisonnement des formalismes syntaxiques est aussi important avec cependant des points de convergence. Ceux ci rendent ainsi possible des conversions entre formalismes syntaxiques (par exemple entre TAG et HPSG ou HPSG et CFG) ou vers des formalismes plus ?op?rationnels?. Certaines techniques d'analyse sont ? g?n?riques ? et utilisables pour plusieurs formalismes. Certains syst?mes se veulent multi-formalismes, reposant sur une infrastructure g?n?rique et efficace (pour l'indexation, la gestion des ambigu?t?s, l'unification, gestion de la m?moire par partage ou copie de structures,...). Enfin la notion de lexicalisation des grammaires transcende largement les formalismes. D'autre part, la g?n?ralisation progressive des analyseurs syntaxiques soul?ve la question de leur ?valuation. Th?me : ------------------------------------------------------------------------ L'objectif de ce num?ro est de mieux comprendre l'ensemble des approches et techniques utilis?es en analyse syntaxique et surtout d'en mieux cerner les convergences et compl?mentarit?s. La liste suivante non exhaustive ?num?re divers sujets pertinents pour cet appel. - Convergence de formalismes syntaxiques - Conversions entre formalismes - Formalismes op?rationnels ou descriptifs - Convergence et compl?mentarit? des approches d'analyse syntaxique - Robustesse (traitement des mots inconnus, correction d'erreurs) - Lexicalisation - Int?gration de m?thodes stochastiques - Analyse en cascade ou approches globales - ?volution des approches pour de nouveaux formalismes - Optimisations (g?n?riques) des analyseurs - strat?gies d'analyse - gestion de l'ambigu?t? - techniques d'indexation - gestion m?moire (partage et copie de structures) - Passage aux grammaires ? large couverture - efficacit? des analyseurs - maintenance et modularit? - ?valuation des analyseurs Comit? de lecture sp?cifique ------------------------------------------------------------------------ Pierre Boullier (INRIA, Rocquencourt) John Carroll (Universit? du Sussex, GB) Jean-Pierre Chanod (XRCE, Grenoble) Alexandra Kinyon (Universit? de Pennsylvanie, USA) Guido Minnen (Motorola, USA) Alexis Nasr (LATTICE, Paris) Mark-Jan Nederhof (Universit? de Groningen, Pays-Bas) Gertjan van Noord (Universit? de Groningen, Pays-Bas) Patrick Paroubek (LIMSI, Orsay) Gerald Penn (Universit? de Toronto, Canada) Anoop Sarkar (Universit? Simon Fraser, Canada) Giorgio Satta (Universit? de Padoue, Italie) Manuel Vilares (Universit? de Vigo, Espagne) David Weir (Universit? du Sussex, GB) R?mi Zajac (Systran Software, USA) Format ------------------------------------------------------------------------ Les articles (25 pages maximum) seront soumis au format Word, LaTeX, Postscript ou PDF. Les feuilles de style sont disponibles chez HERMES Langue ------------------------------------------------------------------------ Les articles peuvent ?tre ?crits en fran?ais ou en anglais. Cependant, les soumissions en anglais ne sont accept?es que pour les auteurs non francophones. Calendrier ------------------------------------------------------------------------ La date limite de soumission est fix?e au 9 Mai 2003. Les personnes qui ont l'intention de soumettre un article sont invit?es ? prendre contact avec ?ric de la Clergerie (Eric.De_La_Clergerie at inria.fr). Les articles seront relus par un membre du comit? de r?daction de la revue TAL et par deux relecteurs du comit? de lecture constitu? sp?cifiquement par les coordinateurs pour ce num?ro. La d?cision du comit? de r?daction sera transmise aux auteurs avant le 1er Juillet 2003. La version d?finitive des articles accept?s sera ? remettre pour le 1er Octobre 2003 pour une publication pr?vue fin 2003. Envoi des articles ------------------------------------------------------------------------ Les articles (25 pages maximum, au format Herm?s) doivent ?tre envoy?s par voie ?lectronique ? Eric.De_La_Clergerie at inria.fr ou par voie postale (version papier en cinq exemplaires) ? l'adresse suivante : ?ric de la Clergerie INRIA Rocquencourt Domaine de Voluceau - B.P. 105 78153 Le Chesnay Cedex, France ====================================================================== Call for papers for the special issue of the TAL journal Title: Evolutions in Parsing Submission deadline: May 9th 2003 Guest Editors: ?ric de la Clergerie (INRIA, France) Martin Rajman (EPFL, Switzerland) http://www.atala.org/tal/appel-syntaxe.html ------------------------------------------------------------------------------ Parsing is a very important component in Natural Language Processing. It still raises many problems, for instance at the level grammatical formalisms or at the level of the algorithmic complexity, especially to handle ambiguity. However, because of recent advances, parsers are nowadays more and more widely used in large scale applications. Many approaches exist in the Parsing community that differ on the methods and objectives. The methods include for instance stochastic parsing, local parsing cascades, or more traditional complete or deep parsing. Objectives range from segmentation into chunks to deep parsing based on wide coverage grammars, including shallow and/or robust parsing. Anyway, these various methods and objectives are not necessarily in opposition and may be perceived as complementary. Despite the large number of existing grammatical formalisms, there are hints of convergences between them which open ways for (partial) conversions between formalisms (for instance between TAG and HPSG or HPSG and CFG) or toward "operational" formalisms. Also, some parsing techniques are "generic" and may be applied for several formalisms. Some parsing systems also aim to be multi-formalisms, relying on generic and efficient infrastructures (indexing, memory management by structure sharing or copying, powerful unification). Finally, the notion of lexicalization is present in most formalisms. Last but not least, the generalization of parsers raises the issue of their evaluation. ------------------------------------------------------------------------------ Themes: The main objective of this special issue is a better understanding of the various approaches and techniques found in Parsing, highlighting the convergences and complementarities that may exist between them. We welcome works on any of the following issues. * Convergence between grammatical formalisms * conversions of formalisms * operational formalisms vs declarative ones * Convergence and complementarity in parsing approaches * robustness (unknown words, error corrections) * lexicalization * Integration of stochastic methods * Cascade parsing vs one-pass parsing * Evolution of parsing techniques for new formalisms * (generic) Optimizations in Parsing * parsing strategies * ambiguity management * chart indexing * memory management (structure sharing and copying) * Wide coverage grammars * parsing efficiency * maintenance and modularity * Parsing evaluation Reviewers ------------------------------------------------------------------------------ Pierre Boullier (INRIA, France) John Carroll (University of Sussex, UK) Jean-Pierre Chanod (XRCE, France) Alexandra Kinyon (University of Pennsylvania, USA) Guido Minnen (Motorola, USA) Alexis Nasr (LATTICE, France) Mark-Jan Nederhof (University of Groningen, NL) Gertjan van Noord (University of Groningen, NL) Patrick Paroubek (LIMSI, France) Gerald Penn (University of Toronto, Canada) Anoop Sarkar (Simon Fraser University, Canada) Giorgio Satta (University of Padua, Italy) Manuel Vilares (University of Vigo, Spain) David Weir (Universit? of Sussex, UK) R?mi Zajac (Systran Software, USA) Format ------------------------------------------------------------------------------ Papers (25 pages maximum) may be submitted in Word, LaTeX, Postscript or PDF. The style sheets are available at HERMES Language ------------------------------------------------------------------------------ Papers may be written either in French or in English (non-French speaking authors only) Schedule ------------------------------------------------------------------------------ The submission deadline is May 9th 2003. People intending to submit a paper should contact ?ric de la Clergerie (Eric.De_La_Clergerie at inria.fr). Articles will be reviewed by a member of the editorial board of the journal (http://www.atala.org/tal/redaction.html) and two external reviewers chosen by the editors of the special issue. Editorial board decisions and referees' reports will be transmitted to the authors by July 1st, 2003. Final versions of accepted papers will be required by October 1st, 2003. Publication is planned for the end of 2003. Submission ------------------------------------------------------------------------------ Submissions (25 pages maximum, following the Hermes style sheet) should be sent either electronically (Eric.De_La_Clergerie at inria.fr), or by surface mail (five copies) to ?ric de la Clergerie INRIA Rocquencourt Domaine de Voluceau - B.P. 105 78153 Le Chesnay 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain?e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh?sion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Fri Apr 4 16:26:13 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Fri, 4 Apr 2003 18:26:13 +0200 Subject: Conf: GDR 2220 : La productivite : regards actuels Message-ID: La productivit? : regards actuels lundi 12 mai 2003 CHU Piti?-Salp?tri?re, salle 408, 4e ?tage 105, boulevard de l'H?pital 75013 - Paris m?tro : Saint-Marcel http://www.biomath.jussieu.fr/adresse-chu-pitie.html Entr?e libre L'action 5 du GDR 2220 ? Description et mod?lisation en morphologie ? vous invite ? la journ?e internationale sur la productivit? qu'elle organise le lundi 12 mai 2003. Vous trouverez les r?sum?s des communications sur le site du GDR : http://gdr-morphologie.linguist.jussieu.fr/journee-productivite . Pour tout renseignement, contactez Georgette Dal : mailto:dal at univ-lille3.fr . Programme : 9h15-9h30 - Ouverture de la journ?e 9h30-10h10 - Georgette Dal [UMR 8528 (CNRS & Un. Lille 3) & GDR 2220] La productivit? : quelques pr?alables 10h10-11h10 - R. Harald Baayen [Interfaculty Research Unit for Language and Speech (IWTS), University of Nijmegen & Max Planck Institute for Psycholinguistics] [titre non encore communiqu?] 11h10-11h30 - Pause 11h30-12h30 - Georgette Dal, Bernard Fradin [UMR 7110 (CNRS & Un. Paris 7) & GDR 2220], Nabil Hathout [UMR 5610 (CNRS & Un. Toulouse-le Mirail) & GDR 2220] & Fanny Meunier [UMR 5596 (CNRS & Un. Lyon 2) & GDR 2220] Productivit?s compar?es : le cas de la suffixation en ET 12h30-14h00 - D?jeuner 14h00-15h00 - Davide Ricca & Livio Gaeta [Dipartimento di Scienze del Linguaggio, Universita' di Torino] Quantitative methods and Italian word formation: A variable-corpus approach to productivity 15h00-16h00 - Anke L?deling [Institut f?r deutsche Sprache und Linguistik, Humboldt-Universit?t zu Berlin] The interaction of qualitative and quantitative aspects of productivity 16h00-16h20 - Pause 16h20-17h20 - Natalia Grabar [ERM 202, INSERM & GDR 2220], Fiammetta Namer [UMR 7118 & GDR 2220] & Pierre Zweigenbaum [ERM 202, INSERM & GDR 2220] Adjectifs d?nominaux: quelle productivit? pour quels corpus? 17h20-17h45 - Cl?ture de la journ?e ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain?e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh?sion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Fri Apr 4 16:26:16 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Fri, 4 Apr 2003 18:26:16 +0200 Subject: Appel: SEPLN 2003 Message-ID: Second Call for Proposals SEPLN 2003 Second Call for Proposals SEPLN 2003 XIX CONGRESO DE LA SOCIEDAD ESPA?OLA PARA EL PROCESAMIENTO DEL LENGUAJE NATURAL (SEPLN) (19th Conference of the Spanish Society for Natural Language Processing - SEPLN) September 10-12, 2003 Universidad de Alcal? de Henares Alcal? de Henares (Madrid) http://oesi.cervantes.es/sepln Introduction The 19th Conference of the Spanish Society for Natural Language Processing (SEPLN) will take place on September 10-12, 2003 in Alcal? de Henares (Madrid, Spain). As in previous editions, the aim of SEPLN for this Conference is to promote the dissemination of research, development and innovation activities conducted by Spanish and foreign researchers in the field of Natural Language Processing (NLP). The conference will provide a forum for discussion and communication to facilitate an effective exchange of knowledge and scientific materials that are necessary for promoting the publication of relevant work and the establishment of means of collaboration with national and international Institutions that are active in this field. Objectives The main motivation of this conference is to provide the business and scientific communities with an ideal forum for presenting their latest research work and developments in the field of Natural Language Processing, as well as to demonstrate the possibilities offered by these solutions and to know about new projects. Consequently, the 19th SEPLN Conference is a meeting place for presenting results and exchanging ideas concerning the present state of development in this field of knowledge. Furthermore, there is the intention of meeting the goal, achieved in previous editions, of identifying future paths for basic research and foreseen software applications, in order to compare them against the market needs. Finally, the conference intends to be an appropriate forum in helping new professionals to become active members in this field. Topics Researchers and businesses are encouraged to send communications, project abstracts or demonstrations related to any of the following topics: Linguistic, mathematic and psycholinguistic models of language Corpus linguistics Monolingual and multilingual information extraction and retrieval Formalisms and grammars for morphological and syntactical analysis Computational Lexicography Monolingual and multilingual text generation Machine translation Speech synthesis and recognition Semantics, pragmatics and discourse Word sense disambiguation NLP industrial applications Automatic textual content analysis Structure of the Conference The Conference will last three days, with sessions dedicated to presenting papers, ongoing research projects, prototype product demonstrations or products connected with topics addressed in the conference. Scientific activities will be complemented by social and tourist activities, allowing attendants to gain a better understanding about the social and cultural dimensions of Alcal? de Henares. Communications Authors are encouraged to send theoretical or system-related proposals, to be presented at the demonstration sessions, earlier than May 16, 2003. Proposals must meet certain format and style requirements Both the delivery and revision of proposals will be done exclusively in electronic format (PostScript or PDF). Proposals will include a title, the complete names of the authors, their address, telephone, fax and e-mail. Proposals will meet the following requirements (concerning the final version, please check the "publication format" section): The proposals will be presented in Spanish or English Inclusion of an abstract (maximum 150 words) Related topic Overall maximum length will be 3,500 words (including the abstract) The proposals will be anonymously revised. Therefore, two separate files will be submitted, one will only include the title and author details, the other will only include the title and the rest of the proposal Final versions (after notification of acceptance) will follow the style requirements that are described in the publication format section in this website Authors will submit their proposals through the following web system: https://chair.dlsi.ua.es/sepln03/submit.html Projects and Demos As in previous editions, the organizers encourage participants to give oral presentations of projects and demos. Depending on the estimated number of oral presentations, any session may be reserved to this purpose. Proposals must meet certain format and style requirements for presentations. For oral presentation of projects to be accepted, the following information must be included: - Project title - Funding institution - Participant groups in the project - Name, affiliation, e-mail and phone number of the project director - Abstract (2 pages maximum) - If a demonstration is to be performed, further information must be included, as indicated below For demonstrations to be accepted, the following information is mandatory: - Name, affiliation, e-mail and phone number of the authors - Abstract (2 pages maximum) - Time estimation for the whole presentation - This information must be received by June 10, 2003 Publication Format The final version of the article will be sent before June 27, 2003 through a web system: https://chair.dlsi.ua.es/sepln03/submit.html - Documents must not include headers or footings - Maximum length will be 8 pages DIN A4 (210 x 297 mm), included references and figures. - In the case of demonstrations and projects, maximum length will be 2 pages. Articles will be sent in Postscript or PDF format. LaTeX format Authors using LaTeX format may download from the Conference website the following style package zip file: latex_new.zip which contains document and bibliography styles, as well as an example showing existing possibilities. Word format Authors using Microsoft Word or compatible may download from the Conference website the following zip file: word_new.zip which includes a pattern file in RTF format and an example showing existing editing possibilities. Important Dates Dates for submission and notifications of acceptance: - Deadline for submitting abstracts: May 16, 2003 - Notification of acceptance: June 20, 2003 - Deadline for submitting the final version: June 27, 2003 - Deadline for submitting projects and demos: June 10, 2003 Program Committee Chairman: Prof. Maximiliano Saiz Noeda (Universitat d'Alacant) max at dlsi.ua.es Members: Prof. Jos? Gabriel Amores Carredano (Universidad de Sevilla) Prof. Toni Badia i Card?s (Universitat Pompeu Fabra) Prof. Manuel de Buenaga Rodr?guez (Universidad Europea de Madrid) Prof.? Irene Castell?n Masalles (Universitat de Barcelona) Prof.? Arantza D?az de Ilarraza (Euskal Herriko Unibertsitatea) Prof. Antonio Ferr?ndez Rodr?guez (Universitat d'Alacant) Prof. Mikel Forcada Zubizarreta (Universitat d'Alacant) Prof.? Ana Mar?a Garc?a Serrano (Universidad Polit?cnica de Madrid) Prof. Koldo Gojenola Galletebeitia (Euskal Herriko Unibertsitatea) Prof. Xavier G?mez Guinovart (Universidade de Vigo) Prof. Julio Gonzalo Arroyo (Universidad Nacional de Educaci?n a Distancia) Prof. Jos? Miguel Go?i Menoyo (Universidad Polit?cnica de Madrid) Prof. Joaquim Llisterri (Universitat Aut?noma de Barcelona) Prof. Javier Mac?as Guarasa (Universidad Polit?cnica de Madrid) Prof. Jos? B. Mari?o Acebal (Universitat Polit?cnica de Catalunya) Prof.? M. Antonia Mart? Anton?n (Universitat de Barcelona) Prof.? Lidia Ana Moreno Boronat (Universitat Polit?cnica de Valencia) Prof. Lluis Padr? (Universitat Polit?cnica de Catalunya) Prof. Manuel Palomar Sanz (Universitat d'Alacant) Prof. Jos? Manuel Pardo Mu?oz (Universidad Polit?cnica de Madrid) Prof.? Natividad Prieto S?ez (Universitat Polit?cnica de Valencia) Prof. Germ?n Rigau (Universitat Polit?cnica de Catalunya) Prof. Horacio Rodr?guez Hontoria (Universitat Polit?cnica de Catalunya) Prof. Kepa Sarasola Gabiola (Euskal Herriko Unibertsitatea) Prof. L. Alfonso Ure?a L?pez (Universidad de Ja?n) Prof.? M? Felisa Verdejo Maillo (Universidad Nacional de Educaci?n a Distancia) Prof. Manuel Vilares Ferro (Universidade de Vigo) Organising Committee Chairman: Mr. Jes?s Antonio Cid Mart?nez, Academic Director at Instituto Cervantes Coordinator: Ms. Isabel Bermejo Rubio, Responsible for the Bureau of Spanish in the Information Society - OESI - at Instituto Cervantes Members: Ms. Eva M? Garc?a Garc?a, Technician at OESI, Instituto Cervantes Ms. Raquel Tapias Aparicio, Technician at OESI, Instituto Cervantes Mr. John Michael Urresti Gra?a, Technician at OESI, Instituto Cervantes Collaborators: Ms. Eva M? G?mez G?mez, Collaborator at OESI, Instituto Cervantes Ms. Rosario Guijarro Huerta, Collaborator at OESI, Instituto Cervantes Further Information Full information is available at the official website of the Conference: http://oesi.cervantes.es/sepln You may also contact the coordinator at any of the following addresses: Secretary of the 19th SEPLN Conference Conference coordinator: Ms. Isabel Bermejo Rubio Oficina del Espa?ol en la Sociedad de la Informaci?n C/ Libreros, 23 28801 Alcal? de Henares (Madrid) Spain Tel.: +34 91 888 72 94 Fax: +34 91 888 18 26 E-mail: sepln at cervantes.es Conference website: http://oesi.cervantes.es/sepln ------------------------------------------------------- ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain?e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh?sion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Fri Apr 4 16:26:19 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Fri, 4 Apr 2003 18:26:19 +0200 Subject: Appel: CSSP 2000 Message-ID: ======================================================================= We apologize if you receive this more than once. ======================================================================= ___ ___ ___ ____ ___ ___ ___ ___ / __)/ __)/ __)( _ \ (__ \ / _ \ / _ \ (__ ) ( (__ \__ \\__ \ )___/ / _/ ( (_) )( (_) ) (_ \ \___)(___/(___/(__) (____) \___/ \___/ (___/ THE FIFTH SYNTAX AND SEMANTICS CONFERENCE IN PARIS OCTOBER 2-4, 2003 SECOND CALL FOR PAPERS THEMATIC SESSION The Syntax and Semantics of Number INVITED SPEAKERS Nirit Kadmon (Tel Aviv University) Manfred Krifka (Humboldt University - Berlin) Robert Levine (Ohio State University) Mark Steedman (Edinburgh University) Anne Zribi-Hertz (Paris 8 University) SUBMISSION DEADLINE April 30, 2003 The fifth Syntax and Semantics Conference in Paris (CSSP 2003) will take place at Paris 7 University, on October 2-4, 2003. The conference welcomes papers combining empirical inquiry and formal explicitness. It aims at favouring comparisons between diverse formal theories of syntax and semantics. The domains of inquiry are syntax, semantics, and the syntax-semantics interface. CSSP conferences combine a general session and a thematic session. The theme for the CSSP 2003 thematic session is the syntax and semantics of Number. Prospective speakers are invited to submit an abstract, no more than two pages long (including figures and references), written in French or English. Abstracts should be sent by e-mail (plain ASCII, rtf, ps or pdf) before April 30 to: cssp03 at linguist.jussieu.fr Authors who are not able to send an electronic version should send two hard copies (one anonymous, one non-anonymous) of the abstract to: Colloque de Syntaxe et Semantique a Paris - Universite Paris 7 - UFRL, Case 7003 - 2 Place Jussieu - 75251 Paris-Cedex 05 - France For more information: Web site: http://www.llf.cnrs.fr/CSSP E-mail: cssp03 at linguist.jussieu.fr ORGANISING COMMITTEE: Claire Beyssade (CNRS-J. Nicod), Olivier Bonami (Chair, Rennes 2), Patricia Cabredo Hofherr (CNRS-Paris 8), Daniele Godard (CNRS-Paris 7) SCIENTIFIC COMMITTEE: Claire Beyssade (CNRS-J. Nicod), Olivier Bonami (Rennes 2), Patricia Cabredo Hofherr (CNRS-Paris 8), Francis Corblin (Paris 4), Daniele Godard (CNRS-Paris 7), Jean-Marie Marandin (CNRS-Paris 7) -- ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain?e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh?sion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Fri Apr 4 16:26:23 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Fri, 4 Apr 2003 18:26:23 +0200 Subject: Appel: ACL-SIGSEM Workshop on The Linguistic Dimensions of Prepositions ... Message-ID: <<< NEW DEADLINE: April 25th !! >>>> Call for Papers : ACL-SIGSEM Workshop on The Linguistic Dimensions of Prepositions and their Use in Computational Linguistics Formalisms and Applications. September 4-6, 2003, Toulouse, France Endorsed by SIGSEM, the ACL's Special Interest Group in Computational Semantics. A great deal of attention has been devoted in the past ten years in the linguistic and computational linguistics communities to the syntax and the semantics of nouns, verbs and also, but to a lesser extent, to adjectives. Related phenomena such as quantification or tense and aspect have motivated a number of in-depth studies and projects. In contrast, prepositions have received less attention. The reasons are quite clear: prepositions are probably the most polysemic category, possibly more so than adjectives, and linguistic realizations are extremely difficult to predict, not to mention the difficulty of identifying cross-linguistic regularities. Let us mention, however, several projects devoted to prepositions expressing space, time and movement in AI and in NLP, and also the development of formalisms and heuristics to handle PP attachment ambiguities. Let us also mention the large number of studies in psycholinguistics and in ethnolinguistics around specific preposition senses. Finally, prepositions seem to reach a very deep level in the cognitive-semantic structure of the brain: cognitive grammar developers often use prepositions in their metalanguage, in order to express very primitive notions. An important and difficult question to address, is whether these notions are really primitive or can be decomposed and lexically analysed In argument structure, prepositions often play the crucial role of a mediator between the verb's expectations and the semantics of the nominal argument. The verb-preposition-noun semantic interactions are very subtle, but totally crucial for the development of an accurate semantics of the proposition. Let us note that a number of languages have postpositions or other markers like case instead of prepositions that play a quite similar role. Finally, languages like English have verbal compounds that integrate prepositions (compositionally or as collocations) while others, like Romance languages or Hindi either incorporate the preposition or include it in the prepositional phrase. All these configurations are semantically as well as syntactically of much interest. Prepositions turn out to be a very useful category in a number of applications such as indexing and knowledge extraction since they convey basic meanings of much interest like instruments, means, comparisons, amounts, approximations, localizations, etc. They must necessarily be taken into account---and rendered accurately---for effective machine translation and lexical choice in language generation. Prepositions are also closely related to semantic structures such as thematic roles, semantic templates or frames. From a linguistic perspective, several investigations have been carried out on quite diverse languages, emphasizing e.g., monolingual and cross-linguistic contrasts or the role of prepositions in syntactic alternations. These observations cover in general a small group of closely related prepositions. The semantic characterization of prepositions has also motivated the emergence of a few dedicated logical frameworks and reasoning procedures. The aim of this workshop is to bring together linguists, NLP researchers and practitioners, and AI people in order to define a common ground, to advance the state-of-the-art, to identify the primary issues and bottlenecks, and to promote future collaborations. If appropriate, the workshop will also establish a working group and the development of projects and resources. Paper presentations Both short research notes (3 pages) and longer conference-style papers (up to 10 pages) submissions as well as working session proposals (1 page proposal on a precise topic) are welcome. Papers must be in .ps, .pdf or .doc formats. The 12 point Times new Roman font is preferred, leave about 2.5 cm margins on both sides. More precise formatting instructions will be given for final versions, since a book publication is under preparation. Paper must be sent in electronic form to: stdizier at irit.fr The main topics are: - The syntax of prepositions: formal or descriptive syntax, prepositions in alternations, principles in the syntax of PPs, syntactic and semantic restrictions. General syntactic-semantic principles. Postpositions or other equivalent markers (e.g. case). - Polysemy of prepositions, identification and classification of preposition senses, contrastive uses, metaphorical uses, semantic and cognitive foundations for prepositions. - Descriptions: Potential WordNet / EuroWordNet descriptions of preposition uses, productive uses versus collocations, multi-lingual descriptions: mismatches, incorporation, divergences. Prepositions and thematic roles, prepositions in semantic frameworks (e.g. Framenet.). - Cognitive or logic-based formalisms for the description of the semantics of prepositions, in isolation, and in composition/confrontation with the verb and the NP. Compositional semantics. Logical and reasoning aspects. - The role of prepositions in applications, in particular: * in machine translation * in information extraction * in lexicalization in language generation. - Corpus-based studies that support or challenge any of the approaches described above. - Lexical knowledge bases and prepositions. Prepositions in AI, KR and in reasoning procedures. Deadlines Submission deadline: April 25th, 2003 <<<<< NEW DEADLINE >>>>>> Notification to authors: May 30th Final paper due July 1st (a book publication is under preparation) Registration preferably before July 7th. (to be confirmed) Registration frees will be kept as low as possible, around 100 Euros with lunch. Programme Committee: Nicholas Asher (Austin) Pushpak Bhattacharyya (IIT Mumbai) Harry Bunt (Tilburg) Nicoletta Calzolari (Pisa) Bonnie Dorr (Maryland) Christiane Fellbaum (Princeton) Claire Gardent (CNRS Nancy) Betsy Klipple (Upenn) Alda Mari (ENST Paris) Palmira Marraffa (Lisboa) Martha Palmer (Upenn) James Pustejovsky (Brandeis) Patrick Saint-Dizier (Chair, IRIT, Toulouse) Gloria Vazquez (Lerida) Laure Vieu (IRIT, Toulouse) Contacts : Submissions and inquiries : stdizier at irit.fr and submissions also to : patrick_saintdizier at yahoo.fr Local organizing committee : Farah Benamara, Patrick Saint-Dizier WEB site: www.irit.fr/cgi-bin/voir-congres ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain?e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh?sion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Fri Apr 4 16:26:26 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Fri, 4 Apr 2003 18:26:26 +0200 Subject: Appel: Eurospeech'2003 Message-ID: Dear Colleagues, Given the recent cancelation of ICASSP'03, the Eurospeech'2003 Organizing Committee decided to slightly extend the paper submission deadline until Sunday, April 6, midnight. Please, be aware though that there will be no further extension and that this is the actual final submission deadline! This should thus give you the opportunity to publish updated results related to a planned ICASSP presentation. Of course, this is not an invitation to re-submit the same paper (which is "illegal", and will be closely checked), but to offer you an opportunity to present an updated/enhanced version of it. Also, I think that there were 2 ICASSP special sessions related to speech processing. Of course, again, papers have been published and cannot be "re-cycled". However, if you feel like you missed the opportunity for discussions, etc, and if you believe that the community could benefit from a special session on the same topic at Eurospeech, please let me know. Again, this possibility will be considered at the sole condition that papers would present updated information. Eurospeech special sessions have been selected already and are currently adverstised on the Eurospeech web site, but we would see together what we could do to help you organize this. Best regards, --Herve Bourlard Eurospeech'2003, General Chair ==================================================================================== Eurospeech 2003 / Interspeech 2003 http://www.eurospeech2003.org/ September 1--4, 2003 Geneva, Switzerland CALL FOR PAPERS CALL FOR TUTORIALS CALL FOR SPECIAL SESSIONS ISCA, toghether with the the Eurospeech 2003 /Interspeech 2003 organizing committee, would like to encourage submission of papers for the upcoming conference. The scientific topics are : * Linguistic Modelling of Spoken Language * Phonetics and Phonology * Speech Production * Speech Perception * Discourse and Dialogue * Signal Analysis, Processing and Feature Estimation * Speech Recognition and Understanding * Speaker Authentication * Speech Generation and Synthesis * Spoken Dialogue Systems * Speech Coding and Transmission * Resources, Assessment and Standards * Applications * Education * Other (please specify) No previously published papers should be submitted. Please follow the submission guidelines provided at the URL: http://www.eurospeech2003.org/papers/ TUTORIALS We encourage proposals for half-day pre-conference tutorials. Between 4 and 8 tutorials will be offered on August 31, 2003. Those interested in organizing a tutorial should send a one-page description to Andrzej Drygajlo (andrzej.drygajlo at epfl.ch), with cc to organisers at eurospeech2003.org by January 15. SPECIAL SESSIONS Eurospeech 2003 also welcomes proposals for special sessions. Each special session should consist of 6 invited papers. The topics of the special sessions should be important, new, emerging areas of interest to the signal processing community, yet have little overlap with the regular sessions. They could also be those investigated by members of other societies that are becoming of keen interest to the speech and language community. See the Eurospeech'03 web page at http://www.symporg.ch/eurospeech/Special_session.asp for guidelines. IMPORTANT DATES: Proposals for Tutorials due by: January 15, 2003 Proposals for Special Sessions due by: January 30, 2003 Full and final paper submission deadline: March 28, 2003 Notification of paper acceptance/rejection: June 9, 2003 Early registration: before June 16th, 2003 Conference programme: as of July 15th, 2003 For further information, please refer to the conference web site, at the URL: http://www.eurospeech2003.org/ -- Please see http://www.idiap.ch/local/mailing-lists/ for more infos on IDIAP Mailing lists. ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain?e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh?sion : http://www.atala.org/ ------------------------------------------------------------------------- From thierry.hamon at LIPN.UNIV-PARIS13.FR Thu Apr 10 09:15:22 2003 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Thu, 10 Apr 2003 11:15:22 +0200 Subject: Job: SYSTRAN Message-ID: From: Christiane Panissod Message-ID: <3E91AB4C.8AB2A14A at systran.fr> ********************************************** SYSTRAN, leader in automatic translation solutions, has a position available for a Dutch language trainee (full or part time, from April, 15). The person hired will assist in the development of automatic language translation software at Systran. The work involves creation of electronic dictionaries, assistance in creating linguistic rules, and evaluation of translation results etc. Qualifications : - native command of Dutch - extensive knowledge of the grammar of Dutch - familiarity with linguistic concepts - fluency in English and/or French - basic computer skills required - experience in translation would be helpful Contact C Panissod Mail: panissod at systran.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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain?e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh?sion : http://www.atala.org/ ------------------------------------------------------------------------- From thierry.hamon at LIPN.UNIV-PARIS13.FR Thu Apr 10 09:15:22 2003 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Thu, 10 Apr 2003 11:15:22 +0200 Subject: Q: Corpus of Modern Standard Arabic Message-ID: From: Eric Atwell Message-ID: X-url: http://www.personal.leeds.ac.uk/~scsla/index.html X-url: http://www.computingLEEDS.ac.uk Dear All, I plan to develop a corpus of Modern Standard Arabic, and I would like your views on the types of texts that should be included in this corpus. Answering my questionnaire on this website http://www.personal.leeds.ac.uk/~scsla/index.html will enable me to get a clear idea of the kinds of texts to collect. Also, I welcome any contributions of Arabic text or speech. Thank you Dr Latifa Al-Sulaiti, CVL: Computer Vision and Language research group School of Computing, University of Leeds, LEEDS LS2 9JT TEL: 0113-3437288 FAX: 0113-3435468 EMAIL: latifa at comp.leeds.ac.uk Visit http://www.computingLEEDS.ac.uk - our newsletter for industry ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain?e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh?sion : http://www.atala.org/ ------------------------------------------------------------------------- From thierry.hamon at LIPN.UNIV-PARIS13.FR Thu Apr 10 09:15:22 2003 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Thu, 10 Apr 2003 11:15:22 +0200 Subject: Conf: IWPT 2003 Message-ID: From: Guy Perrier Message-ID: <3E93BEA8.5080002 at loria.fr> X-url: http://iwpt03.loria.fr/ X-url: http://parlevink.cs.utwente.nl/sigparse/ C a l l f o r P a r t i c i p a t i o n IWPT 2003 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 8th International Workshop on Parsing Technologies ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Sponsored by ACL/SIGPARSE 23-25 April 2003 Nancy, France http://iwpt03.loria.fr/ ~~~~ Nancy, "City of Art and History", the historical capital of Lorraine (the north-eastern part of France) welcomes you to the 8th International Workshop on Parsing Technologies. The Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA) in Nancy, France, will host the 8th International Workshop on Parsing Technologies (IWPT'03) from 23 to 25 April, 2003. IWPT'03 continues the tradition of biennial workshops on parsing technology organised by SIGPARSE, the Special Interest Group on Parsing of the Association for Computational Linguistics (ACL). This workshop series was initiated by Masaru Tomita in 1989. The first workshop, in Pittsburgh and Hidden Valley, was followed by workshops in Cancun (Mexico) in 1991; Tilburg (Netherlands) and Durbuy (Belgium) in 1993; Prague and Karlovy Vary (Czech Republic) in 1995; Boston/Cambridge (Massachusetts) in 1997; Trento (Italy) in 2000, and Beijing (China) in 2001. ******************************************** * INVITED SPEAKERS: * * * * Gregory Grefenstette (Clairvoyance Corp) * * Eugene Charniak (Brown University) * * * ******************************************** Program: -------- Three days of invited talks, long papers, short papers and posters and discussions. invited talks: -------------- Eugene Charniak (Brown University), Syntax-based Language Models for Statistical Machine Translation Gregory Grefenstette (Claivoyance Corporation, Pittsburgh), Why Parse? Statistical Processing or Symbolic Processing. accepted papers: ---------------- Miguel A. Alonso, V??ctor J. D??az, Parsing Tree Adjoining Grammars and Tree Insertion Grammars with simultaneous adjunctions. Pierre Boullier, Supertagging: A non-Statistical Parsing-based Approach. Denis B??chet, Incremental parsing of Lambek calculus using proof-net interfaces. Pierre Boullier, Guided Earley Parsing. Anna Corazza, Parsing Strategies for the Integration of Two Stochastic Context-Free Grammars. James Henderson, Generative Versus Discriminative Models for Statistical Left-Corner Parsing. Mark-Jan Nederhof, Giorgio Satta, Probabilistic Parsing as Intersection. Khalil Sima'an, On Maximizing Metrics for Syntactic Disambiguation. Hiroyasu Yamada, Yuji Matsumoto, Statistical Dependency Analysis with Support Vector Machines. Gennaro Costagliola, Vincenzo Deufemia, Visual Language Editors based on LR Parsing Techniques. Kenji Sagae, Alon Lavie, Combining Rule-based and Data-driven Techniques for Grammatical Relation Extraction in Spoken Language. Frederik Fouvry, Constraint relaxation with weighted feature structures. Chad Langley, Alon Lavie, Parsing Domain Actions with Phrase-Level Grammars and Memory-Based Learners. Mark-Jan Nederhof, Giorgio Satta, Stuart M. Shieber, Partially Ordered Multiset Context-Free Grammars and ID/LP Parsing. Joakim Nivre, An Efficient Algorithm for Projective Dependency Parsing. Kilian Foth, Wolfgang Menzel, Subtree Parsing to Speed up Deep Analysis. Accepted Poster Presentations ----------------------------- Philippe Blache, Meta-level constraints for representing interaction between linguistic domains. Vladimir Kadlec, Pavel Smrz, PACE --- Parser Comparison and Evaluation. Mi-Young Kim, Jong-Hyeok Lee, S_clause Segmentation for Efficient Syntactic Analysis in Long Sentences. Yong-Jae Kwak So-Young Park Hoojung-Chung Young-Sook Hwang Hae-Chang Rim, GLR Parser with Conditional Action Model using Surface Phrasal Types For Korean. Souha Hammami Mezghani, Chafik Aloulou, Lamia Hadrich Belguith, Ahmed Hadj Kacem, Impl??mentation du syst??me MASPAR selon une approche multi-agent. Sanghamitra Mohanty, Rakesh Chandra Balabantaray, Intelligent Parsing in Natural Language Processing. [canceled] So-Young Park Yong-Jae Kwak Hoo-Jung Chung Young-Sook Hwang Hae-Chang Rim, Automatic Acquisition of Constraints for Efficient Korean Parsing. Tomasz Obrebski, Dependency parsing using dependency graph for storing alternative structures. For more details, see the Programme page at http://iwpt03.loria.fr/ Registration: ------------- Early registration is possible until March 28; after that date the registration fee will be higher. Please register online using the IWPT'03 web pages at http://iwpt03.loria.fr/ At the web site you can also find information about accomodation and other relevant information. IWPT'03 Organization: --------------------- General Chair: Harry Bunt (Tilburg University, Netherlands) Programme Chair: Gertjan van Noord (University of Groningen, Netherlands) Local Organization Chair: Guy Perrier (LORIA, Nancy, France) Further information ------------------- Additional information about IWPT'03 is available at the URL: http://iwpt03.loria.fr/ At the SIGPARSE site at http://parlevink.cs.utwente.nl/sigparse/ information is available about previous IWPTs, proceedings, books based on IWPTs, and SIGPARSE related activities. ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain?e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh?sion : http://www.atala.org/ ------------------------------------------------------------------------- From thierry.hamon at LIPN.UNIV-PARIS13.FR Thu Apr 10 09:15:22 2003 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Thu, 10 Apr 2003 11:15:22 +0200 Subject: Appel: ELSNET/ENABLER Resources Infrastructure Workshop at ACL2003 Message-ID: From: Steven Krauwer Message-ID: <20030409170511.A15232 at syntax.let.uu.nl> X-url: http://www.elsnet.org/acl2003-workshop X-url: http://www.elsnet.org ACL2003 Resources Information Infrastructure Workshop _________________________________________________________________ Last CALL for PAPERS Towards a Resources Information Infrastructure Workshop at ACL2003 in Sapporo (Japan) July 11 and 12 2003 Organised by ENABLER / ELSNET Description The problem addressed by this workshop is the well-known information problem. People are creating, exploring and exploiting language resources all over the world. Those who are working with resources know a lot about their own and other resources, and they are generally prepared to share this knowledge, their expertise and in many cases even their resources with others via publications in journals, presentations at conferences, and via the web. Unfortunately this information, however public, is not accessible in any systematic way for those who need resources, who want to know what sort of resources exist, how resources should be annotated, which standards to adhere to, which tools to use, etc etc. We will call this problem the 'Resources Information Problem'. The problem has also a geographical dimension: As work on specific languages is very often concentrated in specific parts of the world, much relevant information has a tendency to stay in one geographical place. This is an obstacle for those who are working on these same languages in different parts of the world, and it makes it harder to port knowledge and expertise gained on one language to other languages. The above observation are far from novel, and it would be naive to think that the problems will ever go away. At the same time one can observe that there are organisations (associations, agencies, projects, networks, etc) that have access to parts or fragments of this information and that have their own infrastructures that facilitate access to this information by internal or external people. The purpose of this workshop is to investigate how we can exploit the existing infrastructures to a maximum in order to facilitate world-wide access to information on language resources. The role of the workshop will be to bootstrap this process. Approach * First of all we will try to make an initial map of the language resources landscape world-wide. This map will include actors, organisations, repositories, standards, projects, tool libraries, etc etc. All participants will be asked beforehand to submit pointers to such items. They will be collected and published. * At the workshop we will invite representatives of a number of organisations that can be seen as key actors in the field, and they will be asked to present ideas about the way their organisation could contribute to solving the Resources Information Problem. These ideas could range from very concrete and immediately implementable proposals to longer term and visionary actions. * A round table discussion at the workshop will aim at the creation of convergence, coherence and synergies between the proposed actions. The intended output is a catalogue of actions to facilitate access to resources information that could be implemented (almost) immediately, a skeleton plan for longer term actions, and firm commitment from key players to make these things happen. Target audience Representatives of parties that could play a key role in providing access to resources information, such as (but not limited to) * Resources distribution agencies, e.g. LDC and ELDA/ELRA * Professional organisations, e.g. ACL, ISCA, and their regional branches, e.g. EACL, AACL, JACL, Asian NLP federation * Networks and resources infrastructure projects, e.g. ENABLER, ISLE. ELSNET * Committees, e.g. ICWLR, COCOSDA * National resources or infrastructure projects, e.g. Technolangue, Collate * International actions, e.g. OLAC * Researchers and developers interested in improving the language resources infrastructure for our community Invited and submitted papers We expect to invite some 15 representatives to give their presentations, but in addition we are issuing an open call for papers addressing the resources information problem and possible solutions. These papers will be reviewed in the usual way. Submission format Please submit full papers of maximum 8 pages (including references, figures etc). Authors should follow the main conference ACL style format. Electronic submission only. Send the pdf, postscript, or MS Word form of your submission to: Steven Krauwer (steven.krauwer at elsnet.org) who will also answer any queries regarding the submission. Important Dates Submission deadline for workshop papers: 13 April 2003 Notification of accepted papers: 14 May 2003 Deadline for camera ready copies 29 May 2003 Workshop dates: 11-12 July 2003 Workshop Format It will be a two-day workshop, with invited and submitted presentations in the mornings, and topical panels and round table discussion in the afternoons, including an open meeting of the newly created International Coordination Committee for Written Language Resources. Programme Committee As this workshop is jointly organized by ELSNET and ENABLER (two EU funded projects aimed at providing collaboration infrastructures), we have invited all ca 60 members of the ELSNET and ENABLER Boards to constitute the core programme committee. We may want to invite additional members from Asia and other parts of the world in order to ensure sufficient geographical coverage. A full list of PC members will be published on the workshop website at http://www.elsnet.org/acl2003-workshop The workshop will be jointly chaired by Steven Krauwer (ELSNET) and Nicoletta Calzolari/Antonio Zampolli (ENABLER) Historical note This workshop can be seen as a follow-up of the workshop organised at ACL2000 in Hong Kong, entitled 'Towards infrastructures for global collaboration'. One of the conclusions of this workshop was that the field of language resources would offer good opportunities for collaborative actions, and the first concrete goal was the creation of an international resources federation, a first step towards which is now embodied by the proposal to set up an International Committee for Written Language Resources. The workshop should lead to the definition of concrete actions to be carried out under the auspices of ICWLR, in collaboration with other organisations. Contact info Steven Krauwer (steven.krauwer at elsnet.org), ELSNET (http://www.elsnet.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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain?e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh?sion : http://www.atala.org/ ------------------------------------------------------------------------- From thierry.hamon at LIPN.UNIV-PARIS13.FR Thu Apr 10 09:15:23 2003 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Thu, 10 Apr 2003 11:15:23 +0200 Subject: Appel: GL2003 (Deuxieme Appel) Message-ID: From: Pierrette Bouillon Message-id: <3E952B19.3020501 at issco.unige.ch> X-url: http://issco-www.unige.ch/ X-url: http://issco-www.unige.ch/gl2003.html ============================================================================ 2nd International Workshop on Generative Approaches to the Lexicon (Endorsed by ACL SIGLEX) ============================================================================ Second call for participation May 15-17, 2003 School of Translation and Interpretation, University of Geneva (Switzerland) http://issco-www.unige.ch/gl2003.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 In this second workshop we would like to keep all the above perspectives, but put more of the focus on available on-line lexical resources in order to compare experience. The discussions will be centered, but not limited to, the following topics: * Building new resources * Acquiring lexical information * Maintaining resources * Representing lexical information (i.e. polysemy, collocation links, multiword expressions, predicate-argument structure) * Using lexical information in applications * Specialization and customization for specific applications * Links between different frameworks * Sharing lexical resourcesBuilding Lexical Resources * Multilinguality in the lexicon * Standardization and evaluation The conference will be held over a period of two and a half days. Oral presentations (30 min) and poster presentations are foreseen. Invited speakers include: Nicoletta Calzolari (Istituto Di Linguistica Computazionale, Pisa) Ann Copestake (Cambridge University, Cambridge) Christiane Fellbaum (Princeton University) Charles J. Fillmore(International Computer Science Institute, Berkeley) Alex Lascarides (University of Edinburgh) James Pustejovsky (Brandeis University,Brandeis). GL2003 is: - founded by the Swiss National Science Foundation (FNRS) and the Communications Research Laboratory (Japan) - hosted by University of Geneva, School of Translation and Interpretation, TIM/ISSCO (Switzerland). Organizers: Pierrette Bouillon (School of Translation and Interpretation, TIM/ISSCO, University of Geneva, Switzerland) Kyoko Kanzaki (Communications Research Laboratory, Japan) Program Committee: Susan Armstrong (University of Geneva) Toni Badia (Universitat Pompeu Fabra, Barcelona) Sabine Bergler (Concordia University, Montreal) Federica Busa (MIT, Sloan school of Management) Nicoletta Calzolari (Istituto Di Linguistica Computazionale, Pisa) Ann Copestake (University of Cambridge, Cambridge) Laurence Danlos (University of Paris VII, Paris) Pierre Frath (Marc Bloch University, Strasbourg) Charles J. Fillmore (International Computer Science Institute, Berkeley) Sandiway Fong (NEC, Princeton) Thierry Fontenelle (Microsoft, Seattle) Jacques Jayez (EHESS-CELITH, Paris) Hitoshi Isahara (Communications Research Laboratory, Kyoto) Adam Kilgarriff (ITRI, University of Brighton, Brighton) Alex Lascarides (University of Edinburgh, Edinburgh) Andrei Popescu-Belis (ISSCO/TIM, Geneva) James Pustejovsky (Brandeis University, Boston) Pascale Sebillot (Irisa, Rennes) Evelyne Viegas (Microsoft, Seattle) Piek Vossen (Irion Technologies, Delft) The GL2003 program and registration form are now available at: ============================================================================== http://issco-www.unige.ch/gl2003.html ============================================================================== ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain?e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh?sion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Tue Apr 22 08:19:53 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Tue, 22 Apr 2003 10:19:53 +0200 Subject: Appel: Workshop on MT Evaluation Message-ID: Workshop on MT Evaluation Towards Systematizing MT Evaluation Theme: Estimating the quality of any machine-translation system accurately is only possible if the evaluation methodology is robust and systematic. The NSF and EU-funded ISLE project has created a taxonomy that relates situations and measures for a variety of MT applications. The Framework for MT Evaluation in ISLE (FEMTI) is now available online at http://www.issco.unige.ch/projects/isle/taxonomy3/. The effort of matching these measures correctly with their appropriate evaluation tasks, however, is an area that needs further attention. For example, what effect do user needs have on the functionality characteristics specified in the FEMTI guidelines? To what extent are there unseen relationships in the branches of the taxonomy? How can we judge when a given evaluation measure is appropriate? Issues that come to bear on this question are the automation of MT evaluation, the extension to MT applications such as automated speech-translation, and the evaluation of the very training corpora that an MT system relies on to improve output quality. This workshop welcomes papers for 30-minute presentations on the comparison between MT evaluation measures, studies of the behavior of individual measures (i.e., meta-evaluation), new uses for measures, analysis of MT evaluation tasks with respect to measures, and related topics on this theme. We solicit submissions to the workshop that address some of the following issues, however any other topic related to MT Testing and Evaluation is also acceptable: Machine Translation Evaluation Measures: - Use of existing measures in the ISLE hierarchy (FEMTI guidelines) - New measures and their uses - Matching evaluation requirements (e.g., translation tasks, user profiles) with - measures - Effects of combining measures Evaluation Measures and Languages - Is a metrics effectiveness language independent? - Counting grammatical features for evaluation Evaluation and Domains - Measures for spoken Language translation - Domain-specific evaluation techniques - Using measures to evaluate the quality of a training corpus for a given task Automation vs. Human Testing - Which measures are suitable for automation? - Human/machine scoring comparisons - Human tester agreement: which measures fare best? -------------------------------------------------------------------------------- Submission Format Papers (full papers up to 8 pages in length) must be submitted electronically to: barrett at semanticdatasystems.com , or andrei.popescu-belis at issco.unige.ch Papers are preferred in .pdf, .ps, .rtf, or .txt, format -------------------------------------------------------------------------------- Important Dates: Paper submission deadline: May 11 Notification: June 30 Camera-ready due: July 31 Note: the workshop will be held on September 23, 2003 -------------------------------------------------------------------------------- Also see workshop website for updates: http://www.issco.unige.ch/projects/isle/MTE-at-MTS9.html -------------------------------------------------------------------------------- Contacts Leslie Barrett (Transclick, Inc., New York, NY) Andrei Popescu-Belis (ISSCO/TIM/ETI, University of Geneva) -------------------------------------------------------------------------------- Organizers Leslie Barrett (Transclick, Inc., New York, NY) Maghi King (ISSCO/TIM/ETI, University of Geneva) Keith Miller (MITRE Corp) Andrei Popescu-Belis (ISSCO/TIM/ETI, University of Geneva) -------------------------------------------------------------------------------- Program Committee: Bonnie Dorr (University of Maryland) Eduard Hovy (Information Sciences Institute, University of Southern California) Maghi King (ISSCO/TIM/ETI, University of Geneva) Bente Maegaard (Center for Sprogteknologi, Copenhagen, Denmark) Keith Miller (MITRE Corp.) Martha Palmer (University of Pennsylvania) Ted Petersen (Univesity of Minnesota) Andrei Popescu-Belis (ISSCO/TIM/ETI, University of Geneva) Florence Reeder (MITRE Corp) Nancy Underwood (ISSCO/TIM/ETI, University of Geneva) Michelle Vanni (National Computer Security Center) ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain?e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh?sion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Tue Apr 22 08:19:57 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Tue, 22 Apr 2003 10:19:57 +0200 Subject: Conf: resultats du projet Euromap Message-ID: ******************************************************************************** Progres des technologies de la langue en Europe, la position de la France ******************************************************************************** Apres le succes de son premier seminaire, qui a eu lieu en juillet 2002 et ? l'occasion de la fin du projet Euromap, ELDA organise un deuxieme evenement, dedie aux technologies de la langue, qui aura lieu le lundi 28 avril 2003 au 17, rue Hamelin Paris 16eme (Metro Boissiere ou Iena), de 14h ? 17h30. Ce seminaire sera suivi d'un cocktail gracieusement offert par Euromap France. Ce seminaire portera d'une part sur les resultats du projet Euromap, qui couvrent l'etat des lieux en technologies de la langue en Europe, aussi bien de facon qualificative que quantitative, avec une analyse des differentes initiatives nationales. Par ailleurs une presentation de l'evolution de la scene europeenne sera faite avec une description des nouveaux instruments du 6eme Programme cadre de la Commission europeenne, en particulier l'ERA-NET (l'espace europeen de recherche) et son application aux technologies de la langue. D'autre part, les nouvelles initiatives en Evaluation seront introduites par l'equipe d'ELDA. Et enfin, des representants des ministeres initiateurs du programme Technolangue (le Ministere charge de la Recherche et des Nouvelles Technologies, le Ministere delegue a l'Industrie et le Ministere de la Culture et de la Communication) feront etat de l'avancement du programme. Ce seminaire s'adresse aux developpeurs, integrateurs, chercheurs et utilisateurs des technologies de la langue. Renseignements & inscriptions: ***************************** Les inscriptions sont obligatoires et se font par courrier electronique ? Mahtab Nikkhou, nikkhou at elda.fr, en indiquant votre nom, fonction et vos coordonnees professionnelles, jusqu'au 24 avril 2003 au soir. L'entree au seminaire est gratuite. Programme: ***************** Progres des technologies de la langue en Europe, la position de la France 14h00 Accueil 14h15 Euromap Technologies de la Langue : bilan du projet, presentation du rapport final, analyse comparative des technologies de la langue en France et en Europe Bente Maegaard, Andrew Joscelyne (Euromap) 15h00 Programme Technolangue, avancements et nouvelles orientations Joseph Mariani, Stephane Chaudiron, Jacques Mathieu (Ministere en charge de la Recherche et des Nouvelles Technologies, MINEFI ) 15h45 Activite d'evaluation au sein d'ELDA, projet Evalda- Khalid Choukri 16h15 ERA-NET, Espace europeen de recherche en technologies de la langue, 6eme PCRDT (Commission europeenne) 17h00 Foire aux questions 17h30 Fin du seminaire, Cocktail offert par Euromap France Ce seminaire est organise dans le cadre du projet communautaire "Euromap-Technologies de la Langue". **Euromap** Lance par la Commission europeenne, Euromap Technologie de la Langue est un projet de collecte et de dissemination d'informations, visant a faire la promotion et la cartographie de l'ingenierie linguistique en Europe. Depuis le mois d'octobre 2001, ELDA participe a ce projet en tant que representant de la France, en partenariat avec dix autres pays europeens. Pour en savoir plus cliquez sur http://www.elda.fr/fr/proj/euromap.html (site francais) et http://www.hltcentral.org/euromap (site central). **Technolangue** C'est une action interministerielle destinee a mettre en place de maniere perenne une infrastructure de production et diffusion de ressources linguistiques, d'evaluation des technologies de la langue ecrite et orale, de participation aux instances nationales et internationales de normalisation et de standardisation et de veille informationnelle sur le domaine. Les ministeres concernes sont le Ministere charge de la Recherche et des Nouvelles Technologies, le Ministere delegue a l'Industrie et le Ministere de la Culture et de la Communication. **6eme PCRDT/programme-cadre de R&D IST 2002-2006** Le nouveau programme-cadre communautaire pour des actions de recherche et de developpement technologique presente des changements importants dans le financement de la recherche, en particulier avec les nouveaux instruments que sont les projets integres, les reseaux d'excellence et les possibilites d'une meilleure coordination et integration avec les programmes nationaux. *** ELDA - Agence pour la distribution des ressources linguistiques et l'evaluation *** Creee en 1995, L'Agence pour la distribution des ressources linguistiques et l'evaluation (Evaluation and Language resources Distribution Agency) a pour mission l'identification, la collecte et la promotion de ressources linguistiques dans le but de les rendre disponibles aupres des developpeurs et utilisateurs de systemes lies au traitement de la langue. ELDA est egalement partie prenante de projets d'evaluation (de systemes, outils, applications, etc.), s'occupe de la diffusion de l'information relative au domaine de l'ingenierie linguistique et participe a de nombreux projets francais, europeens et internationaux. Pour en savoir plus cliquez sur: 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain?e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh?sion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Tue Apr 22 08:20:01 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Tue, 22 Apr 2003 10:20:01 +0200 Subject: Appel: EUROLAN'03 : Ontologies and Information Extraction Message-ID: We appologies for multiple posting ===================================== Ontologies and Information Extraction International Workshop held as part of the EUROLAN'03 Summer School July 28 - August 8, 2003 Bucarest, Romania New extended dead-line: 5th May 2003 Call for Papers Information Extraction systems were designed to filter, to select and to classify the increasing amount of information available nowadays, mainly on the Web. Most of them were based on shallow natural language processing techniques, but semantics was not really used, due to the unavailability of generic ontologies. During last years, some generic ontologies become available and a lot of research projets tried to take into account semantic aspects to obtain more precise results for IE systems. Meanwhile, important efforts concentrate on developping tools for semi- automatic building of domain-specific ontologies, based on IE and text- mining techniques. This workshop will provide a forum for discussion between leading names in the field and researchers involved in the development of ontology-based IE systems or semi-automatic tools for building ontologies. We would like to invite researchers, master and Ph.D. students to submit their original and unpublished work to the workshop. Topics of interest include but are not limited to: - semantic annotation; - content-based indexing and retrieval; - robust analysis of language data; - text mining; - platforms for semi-automatic ontology extraction; - formalisms for ontology representations. Submission Requirements Authors are invited to submit a 4-6 pages extended abstract in electronic form (postscript or PDF) by 05th May 2003. Authors of accepted papers should submit the final version in electronic format not later than 15th of June. The documents must be in either postscript or pdf format (PDF is encouraged, but postscript documents are acceptable as well). If you have problems delivering your paper in one of these formats, please contact the organising comittee. Maximum length of paper should be about 10 pages. This workshop uses the same guidelines as EACL-2003. The instructions can be found at http://ic.epfl.ch/~pallotta/ontoIE/. Please do not insert page numbers, headers or footers. If you have any problem following the style please contact the organising committee as soon as possible. All the papers should be send to Amalia.Todirascu at utt.fr =============================================================== Important Dates Submission Deadline: 05th May 2003 Notification of Acceptance: 20th May 2003 Camera-ready Papers: 15th June 2003 Demos of working or under development systems are encouraged. ==================================== Registration People wanting to attend the workshop must be registered at the Eurolan'03 School. Participation to the workshop is open to all Eurolan'03 attendants. Copies of workshop proceedings will be made available. Authors of the papers accepted for presentation at the workshop will benefit of early registration fee no matter the date they register. ==================================== Programme Commitee Nathalie Aussenac-Gilles (IRIT, Toulouse, France) Roberto Basili (University of Rome 2 "Tor Vergata", Italy) Bill Black (UMIST, Manchester, UK) Paul Buitelaar (DFKI, Saarbrucken, Germany) Amedeo Cappelli (University of Pisa, Italy) Paola Merlo (University of Geneva, Switzerland) Malvina Nissim (University of Edinburgh, Scotland, UK) Fabio Rinaldi (University of Zurich, Switzerland) Laurent Romary (LORIA, Nancy, France) Patrick Ruch (EPFL, Lausanne, Switzerland) Horacio Saggion (University of Sheffield, UK) Manuela Speranza (IRST, Trento) Steffen Staab (AISB, University of Karlsruhe, Germany) Valentin Tablan (University of Sheffield, UK) Dan Tufis (Romanian Academy, Bucharest, Romania) Organising commitee Amalia Todirascu (Technological University of Troyes, France) Vincenzo Pallotta (EPFL, Lausanne, Switzerland) ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain?e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh?sion : http://www.atala.org/ ------------------------------------------------------------------------- From thierry.hamon at LIPN.UNIV-PARIS13.FR Thu Apr 24 15:39:58 2003 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Thu, 24 Apr 2003 17:39:58 +0200 Subject: Q: Travaux sur les analyseurs syntaxiques et l'approche multi-agent Message-ID: Date: Fri, 11 Apr 2003 17:47:02 +0200 From: "souha.mezghani at laposte.net" Message-Id: Salut tout le monde, Est ce que vous pouvez me referencier sur des travaux utilisant l'approche multi-agent pour la realisation d'un analyseur syntaxique. merci, Souha ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain?e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh?sion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Fri Apr 25 08:04:50 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Fri, 25 Apr 2003 10:04:50 +0200 Subject: Jobs: U. of Groningen : Prof. of Romance Linguistics Message-ID: University of Groningen Faculty of Arts The post is within the Department of Romance Languages and Cultures. The Faculty of Arts of the University of Groningen has a vacancy for the post of Professor of Romance Linguistics. This chair has been created within the Faculty fast-track regulation and, therefore, the current professor and his successor will operate in tandem until 1 January 2005. The aim of the Faculty fast-track regulation is to enable young talent to join or move through the system faster. Candidates may not be older than 45 years of age - that is, they may not have turned 46 on 1 January of the year following their appointment. Professor of Romance Linguistics VACANCY NUMBER 203122/2731 The discipline covers Romance linguistics in the widest possible sense. The professor will be responsible for and must contribute to the teaching and the research within the scope of the department. The professor appointed should preferably work in the field of Romance Linguistics but must be experienced in the field of French Linguistics. He or she must be a specialist in one or more of the approaches to linguistics. The position co-ordinating and providing teaching in the field of Romance Linguistics co-ordinating and performing research in the field of Romance Linguistics supervising PhD candidates performing administrative and organisational duties deepening and promoting the national and international contacts of the department. Profile We are looking for candidates who will provide enthusiastic leadership to a team which keeps a close watch on the newest developments in the fields of teaching, politics and culture. Interested parties must fulfil the following conditions: be no older than 45 years of age (see above) have a PhD in the field of Romance Linguistics be an experienced lecturer with extensive research experience in the field of Romance Linguistics, with specific expertise in the field of French Linguistics. have good administrative and organisational skills be able to promote interest in the field be prepared to move to the Groningen area. Post The RUG is offering a full-time appointment as Full Professor (A) from 1 September 2003. The salary will be EUR 4,428 - EUR 6,462 per month gross (Collective Labour Agreement (CAO) for Dutch Universities). Information Please contact Prof. G.J. de Haan, dean of the Faculty, tel. +31 (0)50 363 5900, e-mail: g.j.de.haan at let.rug.nl if you would like more information. You can request an information package from the secretary of the Faculty of Arts, Ms. G. Peters-Beuke, tel. +31 (0)50 363 5900. If you would like to draw our attention to suitably qualified candidates, please write to the director of the Department of Personnel and Organisation within two weeks. The closing date for applications is 4.6.2003 Please send your written application and curriculum vitae to: The University of Groningen, Personnel & Organisation Department P.O. Box 72, 9700 AB Groningen, The Netherlands. Please state the vacancy number on the envelope and at the top of your letter. There are a number of interesting vacancies at the RUG. Additional information about vacancies at the RUG is available on the university web site: www.rug.nl The RUG has a special careers advisory service for the partners of new staff who move to the area. The RUG is an equal opportunities employer. Because women are still underrepresented in a number of fields, they are particularly encouraged to apply. University Hospital Groningen, Municipality of Groningen, Hanzehogeschool, Informatie Beheer Groep, Martini Hospital, N.V. Nederlandse Gasunie, province of Groningen, University of Groningen and Groningen Regional Police Force are all members of the Noorderlink co-operation (www.noorderlink.nl). If you work for one of these organisations, please write INTERN at the top of your letter. ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain?e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh?sion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Fri Apr 25 08:04:53 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Fri, 25 Apr 2003 10:04:53 +0200 Subject: ATALA: JOURNEE du 17/05 : EXTENSION DE DATE LIMITE DE SOUMISSION Message-ID: [English version below] EXTENSION DE DATE LIMITE DE SOUMISSION ---------------------------------------------------- JOURNEES de l'ATALA - APPEL A COMMUNICATION Des requ?tes aux questions : nouvelle perspective pour la recherche d'information ? >From queries to questions: new perspective for information retrieval? Date limite de soumission prolong?e au 28 avril - English version below ------------------------------------------- Samedi 17 mai 2003 ENST, rue Barrault, Paris 13eme Organis?e par Brigitte Grau (LIMSI) et Olivier Ferret (CEA-LIST) Face ? une question telle que ?Quelle est la voiture la plus ch?re du monde ??, les moteurs de recherche traditionnels renvoient l?ensemble des documents les plus fortement li?s aux mots de la question, en s?lectionnant ?ventuellement un passage, mais laissent ? la charge de l?utilisateur la t?che d?explorer ces documents afin d?y trouver la r?ponse. L?introduction de la t?che ?Question Answering? lors de l??valuation TREC8 (Text REtrieval Conference), en 1999, est r?v?latrice du besoin sans cesse croissant de disposer de syst?mes de recherche d?information allant au del? de la simple recherche documentaire habituellement propos?e. Cette pression a conduit au d?veloppement de syst?mes capables d?extraire les parties des documents les plus pertinentes par rapport ? une question pos?e, en proposant directement une r?ponse lorsqu?il s?agit d?une question factuelle ou un r?sum? si la requ?te est de nature th?matique. Les syst?mes d?velopp?s dans le cadre des ?valuations TREC de ces derni?res ann?es repr?sentent un premier stade dans la probl?matique d?une recherche d?information ax?e sur la notion de question/r?ponse. Cette probl?matique, esquiss?e dans un roadmap r?cent (cf. http://www-nlpir.nist.gov/projects/duc/roadmapping.html), met en avant des fonctionnalit?s nouvelles ou encore assez embryonnaires dans les syst?mes de recherche d?information actuels: ?valuation de l?existence d?une r?ponse ? une question dans une base de textes, synth?se de r?ponses multiples intra ou inter-documents, dialogue d?aide ? la formulation de requ?te ou encore capacit?s de compr?hension de texte permettant par exemple de reconna?tre des reprises anaphoriques ou de juger de l??ventuelle incompatibilit? de r?ponses multiples. Ces nouvelles fonctionnalit?s imposent aux syst?mes de recherche d?information de mener une analyse plus en profondeur ? la fois des requ?tes qui leur sont adress?es et des documents au sein desquels ils doivent chercher les informations permettant d?y r?pondre. C?est pourquoi la probl?matique des syst?mes de question/r?ponse se situe ? l?intersection de plusieurs domaines: elle poss?de bien entendu un ancrage originel fort dans le domaine de la recherche d?information mais elle fait aussi appel de fa?on importante au traitement automatique des langues (TAL) ainsi que plus ponctuellement ? des domaines tels que l?apprentissage automatique. Typiquement, un syst?me de question/r?ponse s?articule ainsi autour d?un moteur de recherche traditionnel, enrichi en amont par un module d?analyse des questions et en aval par des modules robustes d?analyse des documents assurant l?extraction de passages r?ponses en m?lant l?exploitation de traits linguistiques, aussi bien de nature morphologique, syntaxique ou s?mantique, et l?utilisation de crit?res num?riques, plus classiques en recherche d?information. De ces sp?cificit?s se d?gagent plusieurs axes fort de la probl?matique question/r?ponse telle qu?elle est envisag?e actuellement. Le premier de ces axes est le fait que l?analyse des requ?tes est consid?r?e comme une fonction importante visant ? d?terminer les intentions de l?utilisateur, soit le but de sa recherche, et non plus seulement ? produire un ensemble de mots-cl?s. L?impact de cette analyse sur les r?sultats de la recherche a bien entendu pour objectif d?inciter les utilisateurs ? formuler leurs requ?tes sous une forme suffisamment riche, en l?occurrence des questions en langue naturelle, pour permettre la mise en ?vidence de l?objet de leur recherche. Le second axe concerne la n?cessaire robustesse des modules linguistiques d?analyse des documents. Le probl?me des syst?mes de question/r?ponse a ?t? explor? d?s les premiers travaux en TAL (Lehnert 1977) mais sur des domaines limit?s seulement. Actuellement, m?me si le cas de figure des domaines ferm?s demeure, comme avec les FAQ (Frequently Asked Questions), l?int?r?t se porte majoritairement sur des syst?mes de question/r?ponse en domaine ouvert r?pondant ? des questions de nature factuelle ou encyclop?dique ? partir de tr?s grosses base de textes, voire du WEB. Dans ce cadre, il n?est pas possible de poser de restrictions a priori tant pour ce qui est des domaines abord?s que des types de textes trait?s. Il s?agit l? d?un enjeu important pour le TAL auquel peut contribuer de fa?on significative l?apprentissage automatique. Un dernier axe de cette nouvelle probl?matique de la recherche d?information, en relation ?troite avec le pr?c?dent, concerne la capacit? des syst?mes ? auto-?valuer leurs r?sultats et ? utiliser diff?rents niveaux de traitement. ?tre confront? ? des documents sans possibilit? de contr?le quant ? leur nature ou leur sujet signifie que les modules d?analyse des documents les plus sophistiqu?s, donc les plus fragiles, sont parfois mis en d?faut et produisent des r?sultats moins pertinents que ceux issus de modules moins ?labor?s mais plus robustes. La capacit? ? d?terminer lorsqu?un tel cas de figure se produit et ? le g?rer est sans doute une des cl?s du succ?s de l?utilisation du TAL en recherche d?information. Son impact sur l?architecture des syst?mes d?velopp?s est particuli?rement important. Alors qu?une ?valuation des syst?mes de question/r?ponse en Fran?ais est en cours de pr?paration dans le cadre du r?cent appel Technolangue des minist?res de la Recherche et l?Industrie, l?objectif de cette journ?e de l?ATALA est de faire le point sur l??tat actuel des recherches concernant la probl?matique question/r?ponse et de pr?senter les travaux d?j? r?alis?s dans ce domaine, en particulier dans la sph?re francophone, ou les travaux y contribuant directement. Plus sp?cifiquement, les propositions de communication pourront pr?senter des syst?mes de question/r?ponse dans leur ensemble ou bien des traitements constitutifs de tels syst?mes pourvu qu?ils soient replac?s dans la probl?matique question/r?ponse. Parmi ces traitements, on peut notamment citer: - analyse de questions: typologie de questions, extraction de l?objet de la question, de son contexte, de contraintes s?mantiques - reconnaissance d?entit?s nomm?es:en domaine ouvert, typage fin - extraction de passages - similarit? de repr?sentations syntaxiques, partielles ou compl?tes - outils terminologiques: extraction et reconnaissance de termes et de leurs variantes - appariement question - passage de texte fond?s sur des traits linguistiques: traits morphologiques, syntaxiques ou s?mantiques - extraction et justification des r?ponses: patrons de r?ponse, inf?rences, paraphrase ? La cible privil?gi?e de cette journ?e est constitu?e par des travaux portant sur des bases textuelles importantes ou ? partir du WEB mais les syst?mes de question/r?ponse destin?s ? des domaines restreints ou coupl?s ? des bases de connaissances ou des bases de donn?es peuvent ?galement ?tre concern?s dans la mesure o? certains traitements, tels que l?analyse de questions par exemple, sont similaires. Les propositions de communication pourront ?galement aborder des th?mes plus transversaux en relation avec les syst?mes de question/r?ponse, th?mes parmi lesquels: - l?apprentissage automatique; que ce soit pour acqu?rir sur une large ?chelle des ressources utilisables par un syst?me de question/r?ponse ou plus directement, pour apprendre ? s?lectionner et extraire la r?ponse ? une question; - le multilinguisme: difficult? de passer d?une langue ? une autre, sachant que la plupart des syst?mes ont ?t? d?velopp?s pour l?anglais; possibilit? de poser une question dans une langue et de chercher la r?ponse dans des documents ?crits dans une autre langue; - le WEB: utilisation du WEB en tant que source de connaissances ou de r?ponses; sp?cificit? de la recherche de r?ponses sur le WEB; - le multi-document: fusion et coh?rence de r?ponses multiples. Nous demandons aux auteurs de pr?ciser si leur soumission : 1) concerne des travaux en cours, ou des prises de position; 2) des travaux aboutis du point de vue th?orique ou appliqu?. Soumission (modalit?s) Un r?sum? de 2 ? 3 pages doit ?tre envoy? avant le 28 avril 2003 par courrier ?lectronique en format text, .rtf, .doc ou .pdf ? : Brigitte Grau : Brigitte.Grau at limsi.fr et Olivier Ferret: olivier.ferret at cea.fr Les notifications d'acceptation seront donn?es pour le 5 mai 2003. ---------------------------------------------------------------------- >From queries to questions: new perspective for information retrieval? Facing a question such as ?What is the most expensive car in the world??, classical search engines return the documents that are the most strongly linked to the words of the question, sometimes extract the excerpts where these words are the most numerous, but let the user browse texts to actually find an answer. The creation of the Question Answering (QA) task in the TREC8 evaluation (Text REtrieval Conference) in 1999 is the expression of the increasing need to make information retrieval (IR) systems go further than document retrieval. This need leads to develop systems that are able to extract the parts of documents that are the most relevant in relation to a question, providing either an answer when the question is about a precise fact or a summary when it is a topical question. The systems built for the TREC QA evaluations represent a first stage in a more global view of Information Retrieval that is centered on question answering. This perspective, which is presented in a recent roadmap document (see http://www-nlpir.nist.gov/projects/duc/roadmapping.html), puts forward new functions or functions that are still in an embryonic state in current IR systems: evaluating if an answer to a question exists in a large document collection, using dialog for building a query or text understanding capabilities for dealing with anaphora or determining if several answers are coherent. These new functions can be implemented only if IR systems are able to analyze both queries and documents more deeply. As a consequence, question answering is at the crossing of several research fields: of course, it is grounded in Information Retrieval but it also concerns Natural Language Processing (NLP) in an important way and to some extent, fields such as Machine Learning. Most QA systems are based on a classical search engine that is enhanced by a question analysis module, a set of modules for extracting various linguistic features from documents, such as named entities, terms or syntactic relations, and a module that relies on all these data for extracting answers by mixing linguistic and numerical criteria. Tackling question answering in this way brings to the fore a set of issues that renew the Information Retrieval field. The first of these issues is the fact that in the question answering context, a request is not just a bag of words. Its analysis is an important function that aims at finding user?s intentions, i.e. the goal of its search. Performing such an analysis must have an influence on results in such a way that it leads users to express their requests by the means of true questions. A second issue raised by question answering is the need for robustness for the linguistic modules that analyze documents. The question answering problem was already investigated by some early work in the NLP field (Lehnert 1977) but only in restricted domains. At the moment, even if performing question answering in a restricted domain, for instance to query FAQ (Frequently Asked Questions), is still interesting, the main interest focuses on open-domain QA systems that answer to facto?d questions from very large collections of documents or from the WEB. In these two cases, it is not possible to set a priori restrictions about the type of the documents or their topics. As a consequence, robustness is an important issue for the use of NLP in Information Retrieval and Machine Learning can significantly contribute to it. The last aspect of this new viewpoint on information retrieval, closely linked to the previous one, is the capability for a system to auto-evaluate its results and to deal with incomplete results. When the type and the topic of the documents that are processed are not restricted, the most sophisticated modules that analyze them, which are also the most brittle ones, sometimes fail or provide worst results than rougher but more robust modules. The ability to determine when such a case happens and then to manage it is certainly one of the key for a successful use of NLP in Information Retrieval. Its impact on the design of question answering systems is particularly important. While an evaluation of question answering systems for French is beginning in the context of the Technolangue project, from the French ministry of Research and the French ministry of Industry, the aim of this ATALA workshop is to give an overview of the work done in a question answering perspective, especially in the Francophone community. More precisely, submissions will present a question answering system as a whole or will focus on one of its processes provided that it is put in the question answering context. These processes include but are not limited to: - question analysis: question typology, extraction of the question focus, of the question context or more generally, of semantic constraints - named entity recognition: fine-grained named entities, unrestricted domains - passage extraction - full or partial similarity of syntactic structures - terminological tools: extraction et recognition of terms and their variants - text excerpt question matching based on linguistic features: morphological, syntactic or semantic features - extraction and justification of answers: answer patterns, inferences, paraphrase ? This workshop is particularly concerned by papers that focus on QA systems for large collections of documents or the WEB but papers about QA systems for restricted domains or dedicated to knowledge bases or database will also be taken into account as some problems, as question analysis for instance, are shared by the two kinds of systems. Submissions can also tackle cross-domain topics in relation to Question Answering , such as: - QA and machine learning: use of machine learning for selecting and extracting answers to a question but also for building on a large scale resources that are necessary for QA systems; - multilingual and crosslingual QA: what are the difficulties for adapting an existing QA system most of them only work for English to another language; asking a question in a language and searching an answer in a collection of documents in another language; - QA and the WEB: using the WEB as a source of knowledge or a source of answers; what are the specific aspects of searching an answer on the WEB; - multi-document QA: fusion and coherence of multiple answers. Submission: a 2-3 page summary. We ask authors to indicate if their submission: - present in-progress work or is a position paper; - present theoritical or applied completed work. A 2-3-page summary must be sent before April 28, 2003 by e-mail in text, .rtf, .doc or .pdf to: Brigitte Grau : Brigitte.Grau at limsi.fr and Olivier Ferret: olivier.ferret at cea.fr Acceptance notifications will be sent for 5 May 2003. ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain?e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh?sion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Tue Apr 29 16:39:38 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Tue, 29 Apr 2003 18:39:38 +0200 Subject: Conf: 11th ELSNET Summer School on Language and Speech Communication Message-ID: SECOND ANNOUNCEMENT and CALL for PARTICIPATION The 11th ELSNET Summer School on Language and Speech Communication Topic: Language and Speech Technology in Language Learning Lille (France), Monday July 7 - Friday July 18, 2003 Organized by the University of Lille 3 We are happy to announce that registration for the 11th ELSNET Summer School is now open. For this school we have chosen a topic of great relevance to researchers and developers in Europe and in other multilingual environments: the use of language and speech technology in language learning, both of spoken and of written language. The goal of this workshop is to get young researchers on a track that will eventually contribute to an important application area. The underlying vision (or dream) is The automatic animated language tutor. + Audience and aims: We see the school as mainly research and development oriented, and hence the primary audience are researchers, developers and integrators who will make our vision happen (rather than teachers who would use it). Both technological and pedagogical aspects will be taken into consideration The aims are: * to make the students familiar with the main principles and problems of language learning/teaching * to make them familiar with current best practice in computer assisted language learning * to make them familiar with the main challenges in computer assisted language learning Participants are expected to have a general computational background and some familiarity with language or speech research and/or processing. After completion of the summer school participants should be able to function in teams aimed at designing or implementing tools, environments or courses for Computer Assisted Language Learning (abbreviated CALL). + Course programme: The provisonal programme is available at http://www.elsnet.org/ess2003/schedule.html The 2-weeks programme comprises the following courses: * Introduction to CALL (Teacher: Jozef Colpaert, [Univ of Antwerp]) * Introduction to natural language processing for CALL (Teacher: Wolfgang Menzel [Univ of Hamburg]) * Introduction to speech processing for CALL (Teacher: Philippe Delcloque [MSEC Manchester]) * Using NLP tools in CALL (hands-on) (Teacher: Wolfgang Menzel [Univ of Hamburg]) * Using Speech tools in CALL (hands-on) (Teacher: Michael McTear [Univ of Ulster]) * CALL design and interfaces (Teacher: Philippe Delcloque [MSEC Manchester]) * Grammatical and morphological error diagnosis (Teacher: Lars Borin [Univ of Gothenburg]) * Systems for pronunciation training (Teacher: Anne-Marie Oster [KTH Stockholm]) * Building a grammatical CALL system (hands-on) (Teacher: Lars Borin [Univ of Gothenburg]) * Building a speech CALL system (hands-on) (Teacher: Michael McTear [Univ of Ulster]) All students attend the same full programme, except for the hands-on sessions, where students can sign up for either NLP or Speech oriented streams. In special student sessions students can present their own work. The presentations will be published on the ELSNET website. Please note that the number of places for this summer school is limited and that early registration is recommended. The working language of the Summer School will be English. + Fees: Category Registration fee (euro) Students 125 Academic staff 250 Commercial organisations 500 ELSNET members are entitled to a 20% discount + Food and accommodation: The cost of accommodation (on campus) will be 20 euro per night Meals will be free. + Registration, grants and other information: For detailed information about registration procedures and deadlines, fees, accommodation, grant possibilities, venue, course and social programme, etc visit the ESS2003 website at http://www.univ-lille3.fr/ESS2003 or send an email to the local organizers at elsnetadmin at univ-lille3.fr A limited number of grants (covering the cost of accommodation) may be available. Details and application forms will be published on the website. For information about the programme visit the ESS2003 website or http://www.elsnet.org/ess2003 or contact the chair of the programme committee, Steven Krauwer (steven.krauwer at elsnet.org) __________________________________________________________________________ Steven Krauwer, ELSNET coordinator, UiL-OTS, Trans 10, 3512 JK Utrecht, NL phone: +31 30 253 6050, fax: +31 30 253 6000, email: s.krauwer at elsnet.org http://www.elsnet.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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain?e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh?sion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Tue Apr 29 16:39:45 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Tue, 29 Apr 2003 18:39:45 +0200 Subject: Appel : SEPLN 2003 Message-ID: ____________Last Call for Proposals_________________________ SEPLN 2003 XIX CONGRESO DE LA SOCIEDAD ESPA?OLA PARA EL PROCESAMIENTO DEL LENGUAJE NATURAL (SEPLN) (19th Conference of the Spanish Society for Natural Language Processing SEPLN) September 10-12, 2003 Universidad de Alcal? de Henares Alcal? de Henares (Madrid) http://oesi.cervantes.es/sepln Introduction The 19th Conference of the Spanish Society for Natural Language Processing (SEPLN) will take place on September 10-12, 2003 in Alcal? de Henares (Madrid, Spain). As in previous editions, the aim of SEPLN for this Conference is to promote the dissemination of research, development and innovation activities conducted by Spanish and foreign researchers in the field of Natural Language Processing (NLP). The conference will provide a forum for discussion and communication to facilitate an effective exchange of knowledge and scientific materials that are necessary for promoting the publication of relevant work and the establishment of means of collaboration with national and international Institutions that are active in this field. Objectives The main motivation of this conference is to provide the business and scientific communities with an ideal forum for presenting their latest research work and developments in the field of Natural Language Processing, as well as to demonstrate the possibilities offered by these solutions and to know about new projects. Consequently, the 19th SEPLN Conference is a meeting place for presenting results and exchanging ideas concerning the present state of development in this field of knowledge. Furthermore, there is the intention of meeting the goal, achieved in previous editions, of identifying future paths for basic research and foreseen software applications, in order to compare them against the market needs. Finally, the conference intends to be an appropriate forum in helping new professionals to become active members in this field. Topics Researchers and businesses are encouraged to send communications, project abstracts or demonstrations related to any of the following topics: Linguistic, mathematic and psycholinguistic models of language Corpus linguistics Monolingual and multilingual information extraction and retrieval Formalisms and grammars for morphological and syntactical analysis Computational Lexicography Monolingual and multilingual text generation Machine translation Speech synthesis and recognition Semantics, pragmatics and discourse Word sense disambiguation NLP industrial applications Automatic textual content analysis Structure of the Conference The Conference will last three days, with sessions dedicated to presenting papers, ongoing research projects, prototype product demonstrations or products connected with topics addressed in the conference. Scientific activities will be complemented by social and tourist activities, allowing attendants to gain a better understanding about the social and cultural dimensions of Alcal? de Henares. Communications Authors are encouraged to send theoretical or system-related proposals, to be presented at the demonstration sessions, earlier than May 16, 2003. Proposals must meet certain format and style requirements Both the delivery and revision of proposals will be done exclusively in electronic format (PostScript or PDF). Proposals will include a title, the complete names of the authors, their address, telephone, fax and e-mail. Proposals will meet the following requirements (concerning the final version, please check the publication format section): - The proposals will be presented in Spanish or English - Overall maximum length will be 3,500 words - Final versions (after notification of acceptance) will follow the style requirements that are described in the publication format section in the website - The proposals will be anonymously revised. Therefore, the files to be submitted will only include the title remaining the rest of the communication free of any auto-references Authors will submit their proposals through the following web system: https://chair.dlsi.ua.es/sepln03/submit.html Projects and Demos As in previous editions, the organizers encourage participants to give oral presentations of projects and demos. Depending on the estimated number of oral presentations, any session may be reserved to this purpose. Proposals must meet certain format and style requirements for presentations. For oral presentation of projects to be accepted, the following information must be included: - Project title - Funding institution - Participant groups in the project - Name, affiliation, e-mail and phone number of the project director - Abstract (2 pages maximum) - If a demonstration is to be performed, further information must be included, as indicated below For demonstrations to be accepted, the following information is mandatory: - Name, affiliation, e-mail and phone number of the authors - Abstract (2 pages maximum) - Time estimation for the whole presentation This information must be received by June 10, 2003 Publication Format The final version of the article will be sent before June 27, 2003 through a web system: https://chair.dlsi.ua.es/sepln03/submit.html - Documents must not include headers or footings - Maximum length will be 8 pages DIN A4 (210 x 297 mm), included references and figures. - In the case of demonstrations and projects, maximum length will be 2 pages. Articles will be sent in Postscript or PDF format. LaTeX format Authors using LaTeX format may download from the Conference website the following style package zip file: latex_new.zip which contains document and bibliography styles, as well as an example showing existing possibilities. Word format Authors using Microsoft Word or compatible may download from the Conference website the following zip file: word_new.zip which includes a pattern file in RTF format and an example showing existing editing possibilities. Important Dates Dates for submission and notifications of acceptance: - Deadline for submitting abstracts: May 16, 2003 - Notification of acceptance: June 20, 2003 - Deadline for submitting the final version: June 27, 2003 - Deadline for submitting projects and demos: June 10, 2003 Program Committee Chairman: Prof. Maximiliano Saiz Noeda (Universitat dAlacant) Members: Prof. Jos? Gabriel Amores Carredano (Universidad de Sevilla) Prof. Toni Badia i Card?s (Universitat Pompeu Fabra) Prof. Manuel de Buenaga Rodr?guez (Universidad Europea de Madrid) Prof.? Irene Castell?n Masalles (Universitat de Barcelona) Prof.? Arantza D?az de Ilarraza (Euskal Herriko Unibertsitatea) Prof. Antonio Ferr?ndez Rodr?guez (Universitat dAlacant) Prof. Mikel Forcada Zubizarreta (Universitat dAlacant) Prof.? Ana Mar?a Garc?a Serrano (Universidad Polit?cnica de Madrid) Prof. Koldo Gojenola Galletebeitia (Euskal Herriko Unibertsitatea) Prof. Xavier G?mez Guinovart (Universidade de Vigo) Prof. Julio Gonzalo Arroyo (Universidad Nacional de Educaci?n a Distancia) Prof. Jos? Miguel Go?i Menoyo (Universidad Polit?cnica de Madrid) Prof. Joaquim Llisterri (Universitat Aut?noma de Barcelona) Prof. Javier Mac?as Guarasa (Universidad Polit?cnica de Madrid) Prof. Jos? B. Mari?o Acebal (Universitat Polit?cnica de Catalunya) Prof.? M. Antonia Mart? Anton?n (Universitat de Barcelona) Prof.? Lidia Ana Moreno Boronat (Universitat Polit?cnica de Valencia) Prof. Lluis Padr? (Universitat Polit?cnica de Catalunya) Prof. Manuel Palomar Sanz (Universitat dAlacant) Prof. Jos? Manuel Pardo Mu?oz (Universidad Polit?cnica de Madrid) Prof.? Natividad Prieto S?ez (Universitat Polit?cnica de Valencia) Prof. Germ?n Rigau (Universitat Polit?cnica de Catalunya) Prof. Horacio Rodr?guez Hontoria (Universitat Polit?cnica de Catalunya) Prof. Kepa Sarasola Gabiola (Euskal Herriko Unibertsitatea) Prof. L. Alfonso Ure?a L?pez (Universidad de Ja?n) Prof.? M? Felisa Verdejo Maillo (Universidad Nacional de Educaci?n a Distancia) Prof. Manuel Vilares Ferro (Universidade de Vigo) Organising Committee Chairman: Mr. Jes?s Antonio Cid Mart?nez, Academic Director at Instituto Cervantes Coordinator: Ms. Isabel Bermejo Rubio, Responsible for the Bureau of Spanish in the Information Society OESI at Instituto Cervantes Members: Ms. Eva M? Garc?a Garc?a, Technician at OESI, Instituto Cervantes Ms. Raquel Tapias Aparicio, Technician at OESI, Instituto Cervantes Mr. John Michael Urresti Gra?a, Technician at OESI, Instituto Cervantes Collaborators: Ms. Eva M? G?mez G?mez, Collaborator at OESI, Instituto Cervantes Ms. Rosario Guijarro Huerta, Collaborator at OESI, Instituto Cervantes Advisors: Ms. Esmeralda de Luis Mart?nez, Chief at the Department of External and Institutional Relations, Instituto Cervantes Ms. Gloria Gamarra Alonso, Technician at the Department of External and Institutional Relations, Instituto Cervantes Further Information Full information is available at the official website of the Conference: http://oesi.cervantes.es/sepln You may also contact the coordinator at any of the following addresses: Secretary of the 19th SEPLN Conference Conference coordinator: Ms. Isabel Bermejo Rubio Oficina del Espa?ol en la Sociedad de la Informaci?n C/ Libreros, 23 28801 Alcal? de Henares (Madrid) Spain Tel.: +34 91 888 72 94 Fax: +34 91 888 18 26 E-mail: sepln at cervantes.es Conference website: http://oesi.cervantes.es/sepln ____________________________________________________ Oficina del Espa?ol en la Sociedad de la Informaci?n C/ Libreros, 23 28801 Alcal? de Henares (Madrid) Tfno.: 91 888 72 94; Fax: 91 888 18 26 informaoesi at cervantes.es http://oesi.cervantes.es ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain?e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh?sion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Tue Apr 29 16:39:51 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Tue, 29 Apr 2003 18:39:51 +0200 Subject: Soft: Unitex: logiciel de traitement de corpus Message-ID: Bonjour, le laboratoire d'informatique de l'Universit? de Marne-la-Vall?e a mis en ligne un logiciel de traitement de corpus nomm? Unitex. Ce syst?me permet d'appliquer sur des textes des dictionnaires ?lectroniques de mots simples et de mots compos?s. Il est ensuite possible de rechercher des motifs syntaxiques au moyen d'automates ou d'expressions r?guli?res, et de produire des concordances d?crivant les contextes des occurrences trouv?es. Ce logiciel est librement disponible sous licence GPL ? l'adresse http://www-igm.univ-mlv.fr/~unitex Il comprend des ressources pour le fran?ais, l'anglais, le grec, le portuguais, le russe et le tha?. Ce syst?me fonctionne sous Windows et Linux. S?bastien Paumier IGM, Universit? de Marne-la-Vall?e ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain?e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh?sion : http://www.atala.org/ ------------------------------------------------------------------------- From alexis.nasr at LINGUIST.JUSSIEU.FR Tue Apr 29 16:39:58 2003 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Tue, 29 Apr 2003 18:39:58 +0200 Subject: Conf: SIXTH INTEX WORKSHOP Message-ID: ------------------------------------------- SIXTH INTEX WORKSHOP 28-30 May 2003, Sofia, Bulgaria Bulgarian Association of Computational Linguistics (BACL) http://www.bacl.org/6th_intex_workshop_.html LAboratoire de SEmioLinguistique, Didactique et Informatique (LASELDI) http://laseldi.univ-fcomte.fr/intex ------------------------------------------- ------------------------------------ May 28 ------------------------------------ 14:00 15:30: Max Silberztein, Univ. de Franche-Comte: Tutorial for beginners 15:30 16:00: Coffee break 16:00 17:30: Max Silberztein, Univ. de Franche-Comte: Advanced Tutorial ------------------------------------ May 29 ------------------------------------ 9:00 9:30: Svetla Koeva, Stoyan Mihov (Univ. of Sofia, BACL): Welcome speech. 9:30 10:00: Xavier Blanko, Angels CATENA, Sandrine FUENTES, Autonomous Univ. of Barcelona: Macro or microstructure? Improving the lexical coverage of an electronic dictionary while enriching microstructural information 10:00 10:30: Cvetana Krstev, Du??ko Vitas, Tomas Erjavec, Josef Stefan, Univ. of Belgrade: Conversion between Intex and MULTEX-East Morphosyntactic Description 10:30 11:00: Coffee break 11:00 11:30: Xavier Lepetit, Univ. de Copenhague: L'importance des schemas de realisation lexicale dans le TAL : le cas de l'expression du mouvement 11:30 12:00: Liborio Dibattista, Univ. di Bari: Usage d'INTEX pour la construction et la verification de territoires lexicaux scientifiques historiquement determines: la langue de la neurologie de Duchenne de Boulogne ? J.M. Charcot ? Jules Dejerine 12:00 12:30: Jean-Marie Viprey, Univ. de Franche-Comte: DIATAG : convivialite d'etiquetage des ambiguites residuelles ; conception d'outils statistiques de controle 12:30 14:00: Lunch 14:00 14:30: Jorge Baptista, Luis Fahsca, Univ. of Algarve: Mapping, filtering and evaluating impact of ambiguous simple words in Portuguese texts 14:30 15:00: Cristina Mota, Technical Univ. of Lisbon: A renewed Portuguese module for INTEX 4.31 15:00 15:30: Tita Kyriacopoulou, Rania VOSKAKI, Anastasia YANNACOPOULOU, Univ. Aristotle of Thessanoliki: Le module grec d'INTEX : Etat de l'art 15:30 16:00: Coffee break 16:30 17:00: Gordana Pavlovi??-La??eti??, Du??ko Vitas, Cvetana Krstev, Univ. of Belgrade: Dictionary of toponyms in Serbian 17:00 17:30: Svetla Koeva, Ivelina Stoyanova, Svetlozara Lesseva, Sofia Univ.: INTEX as an educational subject in the Master's program of Computational Linguistics at Sofia University ------------------------------------ May 30 ------------------------------------ 9:00 9:30: Max Silberztein, Univ. de Franche-Comte: NOOJ: A Cooperative Object Oriented Architecture for NLP 9:30 10:00: Ibtiha Farawi, Univ. de Franche-Comte: Conjugaison des verbes arabes avec INTEX 10:00 10:30: Ting-Au Cheng, City Univ. of Hong-Kong: Les classifieurs temporels en chinois: etude preliminaire 10:30 11:00: Coffee break 11:00 11:30: Francois Rousselot, Univ. de Strasbourg: Une station d'ingenierie linguistique pour la creation de terminologie et d'ontologie 11:30 12:00: Ivan Obradovi??, Ranka Stankovi??, Gordana Pavlovi??-La??eti??, Cvetana Krstev, Univ. of Belgrade: Application of INTEX in refinement and validation of Serbian WordNet 12:00 12:30: Svetla Koeva, Stoyan Mihov, Sofia Univ.: Semantic Relations in INTEX 12:30 14:00: Lunch 14:00 14:30: Gisele Chevalier, Sylvia Kasparian, Univ. de Moncton: Lexique-grammaire evolutif de l'acadien avec INTEX 14:30 15:00: Sun-mee Bae, Univ. de Marne-la-Vallee: Reconnaissance automatique des noms figes du coreen avec INTEX 15:00 15:30: Stavroula Voyatzi, Univ. Aristotle of Thessanoliki: Description par automate des adverbes de date du grec moderne 15:30 16:00: Lucia Di Palo, Univ. di Bari: Une lecon methodologique en histoire de la medecine : l'application du systeme INTEX au texte "Recherches physiologiques sur la vie et la mort" de Xavier Bichat. Un nouveau moyen d'exploitation de la langue medicale du XVIII siecle 16:00 20:00: Excursion ------------------------------------------------------------------------- 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://listserv.linguistlist.org/archives/ln.html La liste LN est parrain?e par l'ATALA (Association pour le Traitement Automatique des Langues) Information et adh?sion : http://www.atala.org/ -------------------------------------------------------------------------