From thierry.hamon at LIPN.UNIV-PARIS13.FR Tue Mar 2 11:47:25 2004 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Tue, 2 Mar 2004 12:47:25 +0100 Subject: Conf: RIAO 2004, April 26-28, 2004 Message-ID: Date: Sun, 29 Feb 2004 23:53:46 +0100 From: Ibekwe Message-ID: <40426D7A.7070709 at univ-lyon3.fr> X-url: http://www.riao.org Apologies for multiple postings Please find the program for the the seventh RIAO conference. You know that RIAO 2004 will take place in Avignon "Vaucluse", France from April 26 to April 28. Please send this program as much as you can around you. Thank you in advance. You will find more information on the web site and a French version if you need it : www.riao.org. We will be happy to welcome you in Avignon Sincerely G. Grefenstette, co-chair of the program committee information at riao.org RIAO'2004 Coupling Approaches, Coupling Media and Coupling Languages for Information Retrieval PROGRAM University of Avignon (Vaucluse - France) 26-28 Avril 2004 www.riao.org The seventh RIAO conference is organised by: CENTRE DE HAUTES ETUDES INTERNATIONALES D'INFORMATIQUE DOCUMENTAIRE (C.I.D., France) in collaboration with the LIA (Laboratoire d'Informatique d'Avignon - Université d'Avignon) with technical support from l'IRIT (Institut de Recherche en Informatique de Toulouse) in cooperation with the Commissariat à l'Energie Atomique (CEA) LIST Introduction Current content-based information management involves many different disciplines. Information must be retrieved from video, from sound, and from images and graphs. Question answering involves both syntax and semantics. Information classification and filtering involve machine learning and linguistics. In addition, as information technology spreads throughout the world, a wider variety of languages in increasingly complex combinations must be handled. In response to these evolving needs, RIAO'2004 conference will cover the coupling of techniques from different domains to improve information retrieval. RIAO'2004 will present innovative research and developments from all areas of multi-media and multi-language information retrieval. Combination of techniques from disparate domains, will treat retrieval from either a single medium, or across media (indexing one medium for find information in another), or from coupling unstructured and structured information (e.g. exploiting both text and XML structure), or from across languages. RIAO'2004 presents recent scientific progress in these areas with oral presentations, demonstrations of research prototypes, as well as presenting a selection of innovative products present on the market. RIAO (which stands for Recherche d'Information Assistée par Ordinateur ) is organized every three years since 1985. Previous RIAO Conferences were held in Grenoble, France (1985), at MIT in Cambridge Massachussetts. USA (1988), in Barcelona, Spain (1991), in New York USA (1994), at Mc Gill, Montreal (1997), and at the Collège de France, Paris (2000) The conference is organized by the Centre de Hautes Etudes Internationales d'Informatique Documentaire (C.I.D.) in conjunction with various partners. This year's conference presents research from 18 different countries, two invited keynote speeches, 13 sessions of oral presentations, a poster session and a session dedicated to cultural applications. The 51 papers presented, 16 posters, and various presentations will give an overview of the state-of-the-art in this rapidly changing domain. Concurrent to the scientific presentations, a wide variety of innovative applications will be presented by an international selection of companies. Each application was chosen by an Applications Committee using the same criteria of quality and originality as the Scientific Committee for the written scientific communications. Programme RIAO 2004 Monday, April 26 08:00 - 9:30 Registration 09:30 - 10:15 Welcome from officials 10:15 - 11:00 Invited speaker 11:00 - 11:15 Coffee break 11:15 - 12:35 Session 1: Indexing Video, Sound and Images The Físchlár-News-Stories System: Personalised Access to an Archive of TV News Alan Smeaton, Cathal Gurrin, Hyowon Lee, Kieran McDonald, Noel Murphy, Noel O'Connor, Dublin City University Video Summarization Based on User-Defined Constraints and Preferences Vyacheslav Parshin, Liming Chen, Ecole Central de Lyon, Dept. Mathématique-Informatique The TREC VIdeo Retrieval Evaluation (TRECVID): A Case Study and Status Report Alan Smeaton, Dublin City University Wessel Kraaij, TNO TPD Paul Over, NIST CIMWOS: A Multimedia Retrieval System based on Combined Text, Speech and Image Processing Harris Papageorgiou, Prokopis Prokopidis, Lason Demiros, Nikos Hatzigeorgiou, Georges Carayanis, Institute for Language and Speech Processing (ILSP) 12:35 - 13:45 Lunch 13:45 - 15:25 Session 2: Searching across Languages Multilingual Information Retrieval with Asian Languages Jacques Savoy, University of Neuchatel Transitive CLIR Models Wessel Kraaij, TNO Franciska de Jong, University of Twente Interlingual Indexing across Different Languages Kornel Marko, Udo Hahn, Linguistische Informatik Stefan Schulz, Philipp Daumke, Medizinische Informatik Crossing Languages in Text Retrieval via an Interlingua Udo Hahn, Michael Poprat, Linguistische Informatik Stefan Schulz, Joachim Wermter, Kronel Marko, Medizinische Informatik Multilingual document clusters discovery Benoit Mathieu, Christian Fluhr, Romaric Besançon, CEA - LIST/LIC2M 15:25 - 15:55 Break / Demonstrations 15:55 - 16:55 Session 3: Searching and Ontologies Ontologies as Background Knowledge to Explore Document Collections Aussenac Nathalie, Mothe Josiane, IRIT Learning « Generalization/Specialization » Relations between Concepts - Application for Automatically Building Thematic Document Hierarchies Hermine Njike Fotzo, Patrick Gallinari, Lip6 Coupling Information Extraction and Data Mining for Ontology Learning in PARMENIDES Myra Spiliopoulou, University of Magdeburg Fabio Rinaldi, University of Zurich Bill Black, UMIST, Manchester Gian Piero Zarri, CNRS, Paris 16:55 - 17:55 Session 4: Niche Web Systems Combinaison de classifieurs pour le filtrage de documents multi-médias à caractère choquant ou dangereux Bruno Grilheres, EADS S&DE/PSI Rouen Stephan Brunessaux, EADS S&DE Philippe Leray, PSI Rouen Coupling Niche Browsers and Affect Analysis Gregory Grefenstette, Yan Qu, James G. Shanahan, David A. Evans, Clairvoyance Corporation, Pittsburgh, PA, USA Bilingual PRESRI - Integration of Multiple Research Paper Databases - Hidetsugu Nanba, School of Information Sciences, Hiroshima City University Takeshi Abekawa, Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology Manabu Okumura, Suguru Saito, Precision and Intelligence Laboratory, Tokyo Institute of Technology 17:55 - 18:15 Cultural heritage applications Un musée virtuel pour les spécialistes Marie-Françoise Clergeau, Collège de France Fabritius : base de données multilingue en ligne pour les Musées royaux des beaux-arts de Belgique Pierre-Yves Desaive, Musées Royaux des Beaux-Arts de Belgique 18:30 Cocktail in the "Salle de la grande audience" of the Popes' Palace Tuesday, April 27 09:00 - 09:45 Invited speaker 09:45 - 11:05 Session 5: Different Methods and Languages for Question Answering ASKMi: A Japanese Question Answering System based on Semantic Role Analysis Tetsuya Sakai, Yoshimi Saito, Yumi Ichimura, Makoto Koyama, Tomoharu Kokubu, Toshihiko Manabe, Toshiba Corporate R&D Center A Pattern Based Approach to Factoid and Definition Question Answering Horacio Saggion, Mark Greenwood, University of Sheffield Question-Answer Matching : Complementary Methods Karine Lavenus, Jens Grivolla, Laurent Gillard, Patrice Bellot, LIA, Université d'Avignon, France MOQA - Meaning-Oriented Question-Answering Jim Cowie, New Mexico State University, CRL Sergei Nirenburg, University of Maryland, ILIT Tanya Korelsky, CoGenTex, Inc. Stephen Helmreich, New Mexico State University, CRL Benoît Lavoie, CoGenTex, Inc. 11:05 - 11:40 Break / Demonstrations 11:40 - 13:00 Session 6: Image Processing Image Understanding using Domain Knowledge Nicolas Zlatoff, Bruno Tellez, Atilla Baskurt, LIRIS Improving CBIR systems by integrating semantic features Djamel Brahmi, Djemel Ziou, Université de Sherbrooke (Canada) Automatic generation of natural language description for images. Patrick Hede, Pierre-Alain Moëllic, Magali Joint, Joël Bourgeoys, Hubert Naets, CEA LIST/LIC2M Costume: A New Feature for Video Content Indexing Gaël Jaffré, Philippe Joly, IRIT 13:00 - 14:30 Lunch 14:30 - 15:50 Session 7 (parallel session): Cooperative Searching andusers Group Memory Based on the Task Information Jonathan Yu, James Thom, RMIT University Leila Alem, CSIRO BINGO! and DAFFODIL: Personalized Exploration of Digital Libraries and Web Sources Martin Theobald, Max-Planck Institut für Informatik Claus-Peter Klas, Universität Duisburg The Generalized Web Surfer Ayman Farahat, Francine Chen, Palo Alto Research Center Improving Ontology-Based User Profiles Joana Trajkova, Susan Gauch, University of Kansas 14:30 - 15:50 Poster session (parallel session) OWL-based reasoning with retractable inference Carlo Jelmini, Stephane Marchand-Maillet, Viper Group - University of Geneva Browsing and searching e-encyclopaedias Ruth Wilson, Julie Shortreed, Monica Landoni, University of Strathclyde An Experiment with Ontology Mapping using Concept Similarity Robert Villa, Ruth Wilson, Fabio Crestani, University of Strathclyde Coupling OWL with MPEG-7 and TV-Anytime for Domain-specific Multimedia Information Integration and Retrieval Chrisa Tsinaraki, Panagiotis Polydoros, Nektarios Moumoutzis, Stavros Christodoulakis, Lab. of Distributed Multimedia Information Systems and Applications (MUSIC/TUC) Speaker segments regroupment Liming Chen, Aliaksandr Paradzinets, Ecole Centrale de Lyon Rich Document Representation for Document Clustering Azam Jalali, Department of Computer & Electrical Engineering, University of Tehran, Farhad Oroumchian, University of Wollongong in Dubai Audio Documents Analysis And Indexing: Entropy And Dynamism Criteria Liming Chen, Dept. Mathématiques Informatique, Ecole Centrale de Lyon, France Eugeny Bovbel, Hanna Lukashevich, Department of Radiophysics, Byelorussian Denis Mitrofanov, Department of Radiophysics, Byelorussian State University, Belarus Suivi du Locuteur dans des Discours Multimédia Halim Sayoud, Siham Ouamour, USTHB Information retrieval on mixed written and spoken documents Benoit Favre, Patrice Bellot, Jean-François Bonastre, Laboratoire d'Informatique d'Avignon Modélisation de connaissances et fouille d'informations par la cartographie dynamique : application de veille technologique avec Matheo Analyzer Mylene Leitzelman, H Dou, J Kister, Faculte Sciences et Techniques de St-Jérôme Improving the Precision of a Closed-Domain Question-Answering System with Semantic Information Hai Doan-Nguyen, Leila Kosseim, Department of Computer Science, Concordia University Retrieving what's relevant in audio and video: statistics and linguistics in combination Anthony Davis,Phil Rennert, Robert Rubinoff, Tim Sibley, Evelyne Tzoukermann StreamSageToward Tacit Information Retrieval Daniel Memmi, IMAG Grenoble Automating Indexing of Classes and Conferences Jean-Claude Moissinac, François Yvon, Slim Ben Hazez, GET/ENST Indexation automatique de documents par combinaison d'analyses statistiques et terminologiques structurées Lyne Da Sylva, École de bibliothéconomie et des sciences de l'information, Université de Montréal Information Retrieval and Extraction from the Web: the CROSSMARC approach Vangelis Karkaletsis, Constantine Spyropoulos, NCSR "Demokritos", Institute of Informatics & Telecommunications 15:50 - 16:10 Break / demonstrations 16:10 - 17:30 Session 8 (parallel session): User Searching, Studies and Aids Subject knowledge, thesaurus-assisted query expansion and search success Anne Sihvonen, Pertti Vakkari, University of Tampere Fetch: A Personalised Information Retrieval Tool Innes Martin, Joemon Jose, University of Glasgow Interfaces dynamiques de fouille textuelles Javier Couto, Jean-Luc Minel, Laboratoire LaLICC, CNRS-Université Paris-Sorbonne Feedback Mechanisms for a Natural Language Interface: An Application of the Critic Paradigm Johannes Leveling, Fern Universität in Hagen 16:10 - 17:10 Session 9 (parallel session): New views on Relevance Improving the Relevance-based Superimposition model for IR with automatic keyword extraction Teruhito Kanazawa, KYA group Atsuhiro Takasu, Jun Adachi, National Institute of Informatics Evaluation of Retrieval Systems without Predefined Retrieval Unit Arjen de Vries, CWI Gabriella Kazai, Mounia Lalmas, Queen Mary University London Monitoring user-system performance in interactive retrieval tasks Liudmila Boldareva, University of Twente (UT) Arjen de Vries, National Research Institute for Mathematics and Computer Science (CWI) Djoerd Hiemstra, University of Twente (UT) 17:30 - 18:30 Conference given by Michel Laclotte, Directeur Général honoraire of the Louvre Museum « L'École d'Avignon, Deux Siècles de Peinture » 19:00 Guided tour of the "Palais des Papes" 20:15 Conference Dinner Wednesday, April 28 09:30 - 10:50 Session 10: Mono and Multilingual Term Variation Mining textual data through term variant clustering : the TermWatch system Fidelia Ibekwe-Sanjuan, ERSICOM - Université de Lyon 3 Eric Sanjuan, LITA - Université de Metz Knowledge Acquisition from Collections of News Articles to Cross-Language Information Retrieval Fatiha Sadat, National Institute of Informatics (NII) Chinese character expansion for retrieving Japanese paraphrases Takenobu Tokunaga, Yoshiki Tezuka, Hozumi Tanaka, Tokyo Institute of Technology Cross-Language Image Retrieval via Spoken Query Wen-Cheng Lin, Ming-Shun Lin, Hsin-Hsi Chen, Department of Computer Science and Information Engineering, National Taiwan University 10:50 - 11:15 Break / demonstrations 11:15 - 12:35 Session 11: Conceptual, Structural Retrieval, XML Source Code Retrieval using Conceptual Similarity Gilad Mishne, Maarten de Rijke, ILLC, University of Amsterdam Multimodal Indexation of Contrastive Structures in Geographical Documents Antoine Widlöcher, Eric Faurot, Frédérik Bilhaut, GREYC - Université Caën Integrating XLink and XPath to Retrieve Structured Multimedia Documents in Digital Libraries Zhigang Kong, Mounia Lalmas, Department of Computer Science, Queen Mary, University of London Using XML to Query XML - From Theory to Practice Andrei Broder, IBM T.J. Watson Research Center Yoelle Maarek, Yosi Mass, Matan Mandelbrod, IBM Haifa Research Lab 12:35 - 14:00 Lunch 14:00 - 15:40 Session 12: Topic Discovery, Segmentation Summarizing Texts at Various Levels of Detail Marie-Francine Moens, Roxana Angheluta , Rik De Busser, Patrick Jeuniaux, Katholieke Universiteit Leuven Selective Combination of Evidence for Topic Distillation using Document and Aggregate-level Information Vassilis Plachouras, Iadh Ounis, University of Glasgow Fidel Cacheda, University of A Coruna Comparing algorithms for French linear segmentation Laurianne Sitbon, Patrice Bellot, LIA, Université d'Avignon, France Tagging Well-known Arabic Names to Support Question-Answering Systems Saleem Abuleil, Chicago State University Unsupervised Learning with Term Clustering for Thematic Segmentation of Texts Marc Caillet, Jean-François Pessiot, Massih-Reza Amini, Patrick Gallinari, Laboratoire d'Informatique de Paris 6 15:40 - 15:50 Break 15:50 - 17:00 Session 13: Improving Retrieval Combining Positive and Negative Query Feedback in Passage Retrieval Dkaki Taoufiq, Mothe Josiane, IRIT Latent Semantic Indexing with a Variable Number of Orthogonal Factors Georges Dupret Word Pairs in Language Modeling for Information Retrieval Carmen Alvarez, Philippe Langlais, Jian-Yun Nie, Université de Montréal A Query-based Pre-retrieval Model Selection Approach to Information Retrieval Ben He, Iadh Ounis, Department of Computing Science, University of Glasgow 17:00 - 17:30 Closing session Innovative Applications Innovative applications and products related to the conference topics are sought for demonstrations during the three days of the Conference. They will be selected by the international Application committee, on the basis of their innovation and future or present marketability. Selected applications will be given free demonstration spaces. The selection of the innovative applications and products is not finished. The list of accepted ones will be soon available on the RIAO web site Applications and products will be chosen among the following topics: * Multimedia indexing and retrieval systems (text, sound, speech, images, video) * Cross-lingual indexing and retrieval systems * Peer-to-peer text search engines * Cooperative Information Retrieval (grids) * Automatic XML structuring of documents * Automatic metadata generation for text, sound, and images, automatic annotators * Automated ontology construction and annotators * Topic detection and event detection in streaming documents, technology watch, strategy watch * Intelligent message filtering * Intelligent text agents * Parent control and anti-spam control by content filtering * E-learning - response interpretation * Document summarisation -- mono or multilingual, mono or multidocument, profile driven * Topic maps * Domain-specific application of information retrieval and multimedia retrieval: medicine, e-commerce, computer-assisted teaching, video production, etc Demonstrations will be organized all along the conference and short oral presentations will be held in parallel sessions, Monday afternoon (13:45 - 15:25 and 16:55 - 17:55) Committees Program Committee Co-Chairs Christian Fluhr CEA, France Europe, Africa Gregory Grefenstette Clairvoyance Asia, Oceania Bruce Croft Univ. of Mass, Amherst, USA Americas Bruno Bachimont Tech. Univ. of Compiègne Catherine Berrut IMAG, France Georges Carayanis ILSP, Greece Francine Chen PARC, USA Claude Chrisment IRIT, Toulouse, France Roger Dannenberg CMU, USA Franciska de Jong Univ. Twente, Netherlands Claude de Loupy Sinequa, France Renato De Mori Univ. Avignon, France Marc El-Bèze Univ. Avignon, France Pascale Fung Scienc. Tech. Univ., Hong Kong Sadaoki Furui Tokyo Inst. Tech., Japan Jean-Luc Gauvain LIMSI, France Edouard Geoffrois DGA - CTA/CIP, France Julio Gonzalo UNED, Spain Donna Harman NIST, USA David Hawking CSIRO, Australia Ulrich Heid Univ. Stuttgart, Germany Eduard Hovy ISI, Univ. S. California, USA Christian Jacquemin LIMSI, France Boris Katz MIT, USA Elisabeth Liddy Univ. Syracuse, USA Simone Marinai Univ. Florence, Italy José Martinez Univ. Nantes, France Christof Monz Univ. Amsterdam, Netherlands Frank Nack CWI, Netherlands Chahab Nastar LTU, France Jian-Yun Nie Univ. Montréal, Canada Douglas Oard Univ. Maryland, USA Jörg Ontrup Univ. Bielefeld, Germany Gabriella Pasi Univ. Milano, Italy Marie Theresa Pazienza Univ. Roma, Italy Carol Peters CNR, Italy Euripides Petrakis Tech. Univ. of Crete, Greece Marc Pic Advestigo, France Jean-Marie Pierrel INALF, France Jean-Marie Pinon INSA Lyon, France Yan Qu Clairvoyance, USA Steve Renals Univ. Sheffield, Great Britain Tetsuya Sakai Toshiba, Japan Frédérique Segond Xerox, France Bernadette Sharp Staffordshire, Great Britain Alan Smeaton Univ. Dublin, Ireland Tokunaga Takenobu Tokyo Inst. Tech., Japan Simone Teufel Univ. Cambridge, Great Britain Evelyne Tzoukermann ACM, USA Alex van Ballegooij CWI, Netherlands Keith Van Rijsbergen Univ. Glasgow, Great Britain James Z. Wang PennState Univ., USA Ross Wilkinson CSIRO, Australia Zhiping Zheng Univ. Saarland, Germany Applications Committee Chair Chantal Soulé-Dupuy Université de Toulouse, France Michel Benoit Sté Itek, France Robert Bentz Xerox Global Services, France Marie-Françoise Clergeau Collège de France Daniel Confland Jouve, France Max Copperman Kanisa, USA Michel Dureigne EADS, France Bernard Dousset Irit, Univ. Paul Sabatier, France Péré Escorsa Univ. Polytechnic de Catalunya, Spain Muriel Foulonneau Relais Culture Europe, France Christine Jacquet-Pfau Collège de France Dominique Ladiray Insee-Ensac Statistics, Canada Ornella Mich Inst. Trentino di Cultura, Italy Norbert Paquel Canope, France Organisation and Coordination Committee Chair Agnès Beriot Déléguée Générale du C.I.D., France Henriette Allignon C.I.D., France Peter Brodnitz Ogilvy & Mather, Japan Jean Louis d'Arc Fédération France-Poland, France Jean Perrière Administrator, Secretary General, C.I.D., France Sharyn Rosart CASIS, USA Anne Tabutiaux Recherche et Diffusion, France Local Organisation Committee Aurélia Barrière Univ. Avignon, France Stéphane Igounet Univ. Avignon, France (Final list forthcoming) Technical Committee Chair Luc Boulianne C.I.D., Canada Jonathan Albert C.I.D., Canada Max Chevalier Univ. Toulouse, France Jean-Jacques Guilbart Collège de France, France Cécile Laffaire Univ. Toulouse, France Registration Registration fees: * 370 euros for early registration received until April 1, 2004 * 430 euros registration after April 1, 2004 * 320 euros early registration for CID members until April 1, 2004 * 430 euros registration for CID members after April 1, 2004 Registration includes admission to all conference sessions, to prototype and product demonstrations, to coffee breaks, and to the Tuesday night conference dinner. It is possible to reserve extra places at this dinner for 25 euros per person. Student fees: * 170 euros for early registration received until April 1, 2004 * 200 euros registration after April 1, 2004 Student registration includes admission to all conference sessions, to prototype and product demonstrations, to coffee breaks, but not to the Tuesday night conference dinner. Students can reserve a place at this dinner for 25 euros per person. Registration instructions: Please register using the secured payment facilities found on our web site http://www.riao.org/. It is also possible to pay by bank transfer to the following account: Name : CID Bank : Société Générale Branch : Agence Montmartre, 89 rue de Clichy, 75009 Paris, France Account Number : 000 50 06 5481 Rib 06 Bank Number : 30003 Branch Number : 03120 IBAN : FR76 30003 03120 000500065481 06 BIC : SOGEFRPP Payment by check in euros will also be accepted. In this case send your check made out the "C.I.D." along with registration information (as found on the web site) to CID Congrès RIAO'2004 36 bis rue Ballu 75009 Paris France Note: Registration can be canceled (with a 90% reimbursement of registration fees) until April 5, 2004. After this date no reimbursement will be possible. Final Registration: It will also be possible to register and pay registration fees on Sunday evening April 25 at the Hotel DANIELI 17 rue de la République 84000 Avignon between 6 p.m. and 8 p.m. and on-site on Monday April 26 from 8 a.m. It is nonetheless strongly advised to pre-register in order to avoid long lines the first morning, and to take advantage of the reduced early registration fees before April 1, 2004. Each participant must check-in on-site before the conference at the University of Avignon, to receive their badge, the printed proceedings of the conference and the final program. Conference Dinner: The conference dinner will be held at the: "Grenier à Sel" 2, rue du Rempart Saint-Lazare, 84000 Avignon (33) (0) 4 90 27 09 09 http://www.grenieraselavignon.com A map will be distributed at the conferemce. Language: The working language of the conference will be English. In accordance with the French law, it will be possible, nonetheless, to present one's communication in French. Tutorial : Google scientists Vibu Mittal, Shumeet Baluja, and Mehran Sahami plan a tutorial on Web Information Retrieval for Sunday before the conference. This tutorial will be held if a sufficient number of people enroll. Details can be found on the RIAO web site - http://www.riao.org Conference Address: University of Avignon 74, rue Pasteur Avignon Hôtels Rooms have been reserved in a number of local hotels until April 1st, 2004. We recommend that you reserve a room as early as possible. Avignon is very active at the time of the conference. A hotel list is available on the RIAO web site. Transport If you are arriving in Paris at the Paris-Roisy Charles de Gaulle airport, you can take a direct high-speed train to Avignon. Check times online at http://www.sncf.com/indexe.htm . A shuttle leaves from the Avignon-TGV station to downtown Avignon. If you are arriving in Paris at the Orly airport, there are direct flights to Avignon (aéroport national) except on Sundays. Marseille-Marignane is an international airport situated 70 kms from Avignon. You might find a connection arriving there. If you are planning to come through Marseilles, please notify the conference organizers at informations at le-cid.org telling us when you are arriving and we might be able to organize a shuttle to Avignon. Information Centre de Hautes Etudes Internationales d'Informatique Documentaire (C.I.D.) 36 bis rue Ballu 75009 Paris France Tel: (33 / 0) 1 42 85 04 75 Fax: (33 / 0) 1 48 78 49 61 Email: information at le-cid.org Web: http://www.riao.org Revision: February 26, 2004 ------------------------------------------------------------------------- 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 Fri Mar 5 16:57:03 2004 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Fri, 5 Mar 2004 17:57:03 +0100 Subject: Appel: Enhancing and using electronic dictionaries, Coling workshop Message-ID: Date: Thu, 4 Mar 2004 17:50:43 +0900 From: Michael Zock Message-Id: X-url: http://www.limsi.fr/Individu/zock/coling2004workshop.html X-url: http://www.issco.unige.ch/coling2004/ X-url: http://www.issco.unige.ch/coling2004/coling2004downloads.html Enhancing and using electronic dictionaries Michael Zock (Limsi, CNRS) & Patrick St. Dizier (Irit, CNRS) Introduction A dictionary is a vital component of any natural language processing system. Its modern, digital form has considerable potential, especially if it is extended and built in a way compatible with the needs and habits of the average language user. There are many ways to make an electronic dictionary useful for people in their daily tasks of processing language. One could assist 1. reading and writing: adding a transliterator and a morphological generator/parser to a dictionary would put the needed information at the distance of a mouse click. Imagine someone trying to look up the meaning (or translation) of a word in a script he can’t read. 2. language learning: combining dictionaries with a parametrizable flashcard system and a goal-driven exercice generator could help the memorization and automation of words and basic syntactic patterns. In such a system choosing a goal would trigger syntactic templates, filling the latter with words would yield (simple) sentences. 3. lexical access (navigation): structuring the dictionary in a similar way as the human mind, i.e. building an associative network akin to WordNet, but with many more links in particular at the syntagmatic axis, could assist the writer not only in finding new ideas (brainstorming), but also the word he is looking for. Within this framework, word access amounts to entering and navigating in a huge, associative network. To build such a tool one could extract associations from an encyclopedia, label and add them as links to a resource like WordNet. As one can see, there are numerous ways to enhance dictionaries. While the new hardware offers many, sometimes surprising opportunities for novel uses, seizing them requires some rethinking. This is the goal of this one-day workshop. In particular, we’d like to discuss interesting extensions and enhancements of electronic dictionaries. For example, one could consider merging different, thesaurus-like dictionaries and see what kind of conceptual and navigational aids might be added to support the language user: what are his needs, what information is he looking for? Actually, a focus shift might be necessary to move from the data (content and size of the dictionary) to their organisation and access. As, what is a huge dictionary good for, if one cannot find the word one is looking for? Target audience The aim of this workshop is to bring together leading researchers involved in the building of electronic dictionaries to discuss modifications of existing resources in line with the users’ needs (i.e. how to capitalize on the advantages of the digital form). Given the breadth of the questions, we welcome reports on work from many perspectives, including, but not limited, to linguistics, computer science, psycholinguistics, language learning, and ergonomics. We request that each contribution addresses computational aspects. Topics We would like to invite papers addressing any of the following issues: type of information to be stored in the dictionary representation and structuring (indexing) of the data; management, visualization and useability of the data; access (aids for navigation, interface, strategies); acquisition of lexical data (corpus); possibilities for editing entries (annotation, updating); integration (combination of the dictionary with other ressources, writer’s workbench); uses of dictionaries by people (learning/teaching; writing) and by machines (NLP). Submission instructions Papers should be original, hence report on previously unpublished work. Papers simultaneously submitted to other conferences should reflect this fact on the title page. As the review process will not be blind, papers should contain the names and affiliations of authors. Submissions must be electronic only, and should consist of full papers of max. 8 pages (inclusive of references, tables, figures and equations). Project notes and position papers should not exceed 4 pages. Authors should follow the COLING 2004 formating guidelines, available at: http://www.issco.unige.ch/coling2004/coling2004downloads.html. All submissions should be made by email to the following address zock at limsi.fr. They should consist of a single PDF file. Before submitting your document, please verify that all non-standard fonts are correctly embedded in your PDF file (you can do this by disabling the "Use Local Font" option when viewing your document with Adobe's Reader). Formating requirements for the final version of the papers will be posted as soon as they become available. Important dates * Deadline for workshop paper submissions: 1st May 2004 * Notification of workshop paper acceptance: 1st June 2004 * Deadline for camera-ready workshop papers: 15th June 2004 * Workshop Date: 29th August 2004 Organising Committee: * Michael Zock (Limsi-CNRS, Orsay, France) chair * Patrick Saint Dizier (IRIT-CNRS, Toulouse, France) Program Committee: * Antonietta Alonge (University of Perugia, Italy) * Christian Boitet (GETA, Grenoble, France) * Nicoletta Calzolari (ILC-CNR, Pisa, Italy) * Christiane Fellbaum (University of Princeton, USA) * Graeme Hirst (University of Toronto, Canada) * Mathieu Mangeot-Nagata (NII, Tokyo) * Rada Mihalcea (University of North Texas, USA) * Alain Polguère (OLST, University of Montreal, Canada) * James Pustejovsky (University of Brandeis, USA) * Gilles Sérasset (GETA, Grenoble, France) * Patrick Saint Dizier (IRIT-CNRS, Toulouse, France) * Takenobu Tokunaga (Tokyo Institute of Technology, Tokyo, Japan) * Dan Tufis (RACAI, Bucharest, Roumania) * Jean Véronis (University of Aix en Provence, France) * Piek Vossen (Irion Technologies, Delft, The Netherlands) * Leo Wanner (University of Stuttgart, Germany) * Michael Zock (Limsi-CNRS, France) Contact For any queries please contact Michael Zock: zock at limsi.fr ........................................................ Michael ZOCK c/o Professor Tokunaga Department of Computer Science Graduate School of Information Science and Engineering Tokyo Institute of Technology Oookayama 2-12-1, Meguro Ku TOKYO 152-8552/ Japan url: http://www.limsi.fr/Individu/zock/ ------------------------------------------------------------------------- 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 Fri Mar 5 16:57:26 2004 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Fri, 5 Mar 2004 17:57:26 +0100 Subject: Appel: 7th INTEX/NooJ Workshop (2nd CFP) Message-ID: Date: Fri, 05 Mar 2004 16:17:47 +0100 From: Maurel Denis Message-Id: <5.0.0.25.0.20040305161559.00a8ae00 at rabelais.univ-tours.fr> X-url: http://tln.li.univ-tours.fr/JIntex2004/ 7th INTEX/NooJ Workshop Tours, June 7-9 2004 Call for papers - Deadline: March 31, 2004 ORGANIZERS * Laboratoire d'Informatique de l'Université de Tours (E.A. 2101) * Langues et Représentation, Equipe de recherche en linguistique, Université de Tours * LAboratoire de SEmioLinguistique, Didactique et Informatique (E.A. 2281) CALL We invite the submission of papers for the forthcoming seventh INTEX/NooJ workshop, to be held in Tours, June 7-9 2004. INTEX is a linguistic development environment that includes large-coverage dictionaries and grammars, and parses texts of several million words in real time. INTEX includes tools to create and maintain large-coverage lexical resources, as well as morphological and syntactic grammars. Dictionaries and grammars are applied to texts in order to locate morphological, lexical and syntactic patterns, remove ambiguities, and tag simple and compound words. INTEX can build lemmatized concordances of large texts from Finite-State or Context-Free grammars, and can accordingly perform transformation operations on texts in cascade, in order to annotate the text, or to generate paraphrases; these features, when applied in cascade, give INTEX the power of a Turing Machine. INTEX is used as a linguistic platform, an information retrieval system, to teach second languages, as a terminological extractor, as well as to teach computational linguistics to students. NooJ, which uses a new technology, a new linguistic engine and a new interface, is meant to replace INTEX. NooJ's architecture was presented in the 5th INTEX Workshop (Marseille, June 2002) and its first alpha version was demoed at the 6th INTEX Workshop (Sofia, May 27-29 2003). As in the previous workshops (1996, 1999, 2000, 2001, 2002 and 2003), this meeting will be the opportunity for INTEX and NooJ users, as well as other researchers interested in NLP, to meet and to exchange their experience of development, research or teaching. It will also be the occasion to present the recent developments of NooJ. Please, send before March 31st 2004 a one-page abstract to Denis Maurel by email. The abstract, in French or English, should contain the title of the article, name, author affiliations, surface mail and electronic address of each author. All papers will be reviewed by the program committee. Authors will be notified whether their papers are accepted or rejected by April 15th 2004. The timeslot is 30 minutes for presentations (including 5 minutes for discussions). After the conference, authors will be invited to send a definitive version of their papers for publishing. We are planning to combine a subset of the proceedings of the 6th and the 7th INTEX Workshops in a published volume. PROGRAM COMMITTEE * Xavier Blanco (Universidad Autonoma de Barcelona, Spain) * Gisèle Chevalier (Université de Moncton, Canada) * Ibekwe-SanJuan Fidelia (Université de Lyon 3, France) * Nathalie Friburger (LI, Université de Tours, France) * Svetla Koeva (BACL, IBL - BAS, Sofia, Bulgaria) * Stoyan Mihov (BACL, CLPP - BAS, Sofia, Bulgaria) * Denis Maurel (LI, Université de Tours, France) * Paul Sabatier (LIM, CNRS, Marseille, France) * Agata Savary (LI, Université de Tours, France) * Henrik Selsoe Sorensen (Copenhagen Business School, Danemark) * Max Silberztein (LASELDI, Université de Franche-Comté, France) * Tamas Varadi (Hungarian Academy of Sciences, Hungary) * Dusko Vitas (MATF, University of Belgrade, Serbia) DEADLINES Submission due date: March 31, 2004 Notification date: April 15, 2004 Registration: May 1, 2004 Camera ready date: June 30, 2004 NooJ TUTORIALS by Max Silberztein * Initiation Tutorial, 20 persons maximum * Teaching Linguistics with NooJ, 20 persons maximum REGISTRATION FEE The registration fee for the workshop is 30 euros for researchers, 15 euros for students and 40 euros for other categories. The conference will begin on Monday morning and last till Wednesday evening. During the Conference there will be a reception on Monday evening and an optional excursion on Tuesday afternoon. CONTACT denis.maurel at univ-tours.f max.silberztein at univ-fcomte.fr Web site: http://tln.li.univ-tours.fr/JIntex2004/ ------------------------------------------------------------------------- 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 Fri Mar 5 16:58:39 2004 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Fri, 5 Mar 2004 17:58:39 +0100 Subject: Appel: Bulag, Divergence in translation between Asian languages and French Message-ID: Date: Fri, 5 Mar 2004 09:00:10 +0800 From: "CHAO Hui-Lan\(趙蕙蘭\)" Message-ID: <010401c4024d$3681a560$1fa57f8c at chen> X-url: http://tesniere.univ-fcomte.fr/ressources/blgmoden.rtf Call for papers BULAG Special number «Divergence in translation between Asian languages and French» Context One single and same idea can be verbalized in various ways depending on the languages employed; texts in different languages which are the result of translation reveal divergences at all linguistic levels. Such divergences are due to what? The languages origin is evidently not the only reason, every language possessing its own lexicon, syntax and pragmatics. Moreover, a given text, that is generated (and interpreted as well) in a communicative situation with our cognitive luggage and socio-cultural background, constitutes a body which is complex and whose components are connected synergically and this too, in a way that is appropriate for each language. In this context, the aim of this number of the BULAG is to shed light on questions such as: «what is the nature of the divergence observed in translated texts?, «what are the sources of this divergence?, and «what are the processes which enable eliminating diversity between languages in order to obtain semantic equivalence? Topics The following are privileged topics (which does not exclude others that are related to the subject): Linguistics/translation - Translation divergence under its multiple linguistic facets - Resolution of translation divergence for semantic equivalence Applied linguistics - Tools used for studies on translation divergence - Machine translation and Computer Aided Translation focusing on partial or total restructuring of translation divergences Important dates Submission deadline: June 20, 2004 Author notification: July 30, 2004 Final version (ready for reproduction): October 1, 2004 Submission guidelines The paper is to be written in English or French and sent by preference using electronic mail to the following addresses: huilan at mail.wtuc.edu.tw kyoko.kuroda at nifty.ne.jp In case of the impossibility of sending the paper by electronic mail, a submission sent by post will be accepted. A diskette and a paper copy of the contribution are to be sent to the following address: Hui-Lan CHAO French Department Wenzao Ursuline College of Languages 900, Mintsu 1st Road, 807 Kaohsiung, Taiwan Information concerning the paper's format: RTF format is to be employed. The paper should be a document of 5000 words maximum. An RTF format model for the paper can be downloaded from the following address: http://tesniere.univ-fcomte.fr/ressources/blgmoden.rtf Coordinators Hui-Lan CHAO and Kyoko KURODA Contact huilan at mail.wtuc.edu.tw kyoko.kuroda at nifty.ne.jp ------------------------------------------------------------------------- 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 Fri Mar 5 16:57:57 2004 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Fri, 5 Mar 2004 17:57:57 +0100 Subject: Appel: FOIS-2004 Message-ID: Date: Fri, 5 Mar 2004 13:14:56 +0100 From: "Jos Lehmann" Message-ID: <024001c402ab$809f4040$f0419296 at ip.rm.cnr.it> X-url: http://www.fois.org APOLOGIES FOR MULTIPLE COPIES ==== Call for Papers FOIS-2004 International Conference on Formal Ontology in Information Systems http://www.fois.org November 4-6, 2004, Torino (Italy) == Just as ontology developed over the centuries as part of philosophy, so in recent years ontology has become intertwined with the development of the information sciences. Researchers in such areas as artificial intelligence, formal and computational linguistics, biomedical informatics, conceptual modeling, knowledge engineering and information retrieval have come to realize that a solid foundation for their research calls for serious work in ontology, understood as a general theory of the types of entities and relations that make up their respective domains of inquiry. In all these areas, attention has started to focus on the content of information rather than on just the formats and languages in terms of which information is represented. The clearest example of this development is provided by the many initiatives growing up around the project of the Semantic Web. And as the need for integrating research in these different fields arises, so does the realization that strong principles for building well-founded ontologies might provide significant advantages over ad hoc, case-based solutions. The tools of Formal Ontology address precisely these needs, but a real effort is required in order to apply such philosophical tools to the domain of Information Systems. Reciprocally, research in the information science raises specific ontological questions which call for further philosophical investigations. The purpose of FOIS is to provide a forum for genuine interdisciplinary exchange in the spirit of a unified ontological analysis effort. Although the primary focus of the conference is on theoretical issues, methodological proposals as well as papers dealing with concrete applications from a well-founded theoretical perspective are welcome. == Invited Speakers Peter Gärdenfors, Lund University Cognitive Science, Sweden Amie Thomasson, Department of Philosophy, University of Miami, USA == Deadlines and Further Information Abstracts due May 3, 2004 Final submissions May 7, 2004 Acceptance Notification: June 25, 2004 Submission of camera-ready paper: July 30, 2004 Proceedings will be published by IOS Press and available at the conference. Submission is a two-step procedure: first abstracts, then full papers. Submitted papers must not exceed 5000 words (including bibliography). Abstracts should be less than 300 words. Electronic submission via the website is strongly preferred; if unavailable, submission via email or postal mail is possible. For details see: http://www.fois.org == Conference Chair Nicola Guarino (ISTC-CNR, Trento, Italy) nicola.guarino at loa-cnr.it == Program Chairs Achille Varzi (Columbia University, New York, USA) achille.varzi at columbia.edu Laure Vieu (IRIT-CNRS, Toulouse, France) laure.vieu at irit.fr == Local Chairs Maurizio Ferraris (University of Torino, Italy) ferraris at cisi.unito.it Leonardo Lesmo (University of Torino, Italy) lesmo at di.unito.it == Publicity Chair Jos Lehmann (ISTC-CNR, Rome, Italy) joslehmann at www.ip.rm.cnr.it == Topics We seek high-quality papers on a wide range of topics. While authors may focus on fairly narrow and specific issues, all papers should emphasize the relevance of the work described to formal ontology and to information systems. Papers that completely ignore one or the other of these aspects will be considered as lying outside the scope of the meeting. Topic areas of particular interest to the conference are: Foundational Issues . Kinds of entity: particulars vs. universals, continuants vs. occurrents, abstracta vs. concreta, dependent vs.independent, natural vs. artificial . Formal relations: parthood, identity, connection, dependence, constitution, subsumption, instantiation . Vagueness and granularity . Identity and change . Formal comparison among ontologies . Ontology of physical reality (matter, space, time, motion, ...) . Ontology of biological reality (genes, proteins, cells, organisms, ...) . Ontology of mental reality and agency (beliefs, intentions and other mental attitudes; emotions, ...) . Ontology of social reality (institutions, organizations, norms, social relationships, artistic expressions, ...) . Ontology of the information society (information, communication, meaning negotiation, ...) . Ontology and Natural Language Semantics, Ontology and Cognition Methodologies and Applications . Top-level vs. application ontologies . Ontology integration and alignment; role of reference ontologies . Ontology-driven information systems design . Requirements engineering . Knowledge engineering . Knowledge management and organization . Knowledge representation; Qualitative modeling . Computational lexica; Terminology . Information retrieval; Question-answering . Semantic web; Web services; Grid computing . Domain-specific ontologies, especially for: Linguistics, Geography, Law, Library science, Biomedical science, Ebusiness, Enterprise integration, ... == Programme Committee Bill Andersen, OntologyWorks, USA Nicholas Asher, Dept of Philosophy, University of Texas at Austin, USA Nathalie Aussenac-Gilles, Research Institute for Computer Science, CNRS, Toulouse, France John Bateman, Dept of Applied English Linguistics, University of Bremen, Germany Brandon Bennett, Division of Artificial Intelligence, University of Leeds, UK Andrea Bottani, Dept of Philosophy, University of Bergamo, Italy Joost Breuker, Dept of Computer Science & Law, University of Amsterdam, The Netherlands Roberto Casati, Jean Nicod Institute, CNRS, Paris, France Werner Ceusters, Language & Computing, Belgium Tony Cohn, Division of Artificial Intelligence, University of Leeds, UK Robert Colomb, School of Computer Science and Electrical Engineering, University of Queensland, Australia Ernest Davis, Dept of Computer Science, New York University, USA Martin Dörr, Institute of Computer Science, FORTH, Heraklion, Greece Carola Eschenbach, Dept for Informatics, University of Hamburg, Germany Jérôme Euzenat, INRIA Rhône-Alpes, Grenoble, France Christiane Fellbaum, Cognitive Science Laboratory, Princeton University, USA & Berlin Brandenburg Academy of Sciences and Humanities, Berlin, Germany Maurizio Ferraris, Dept of Philosophy, University of Torino, Italy Antony Galton, School of Engineering and Computer Science, University of Exeter, UK Aldo Gangemi, Institute of Cognitive Sciences and Technologies, CNR, Rome, Italy Peter Gärdenfors, Lund University Cognitive Science, Sweden Pierdaniele Giaretta, Dept of Philosophy, University of Padova, Italy Michael Gruninger, Institute for Systems Research, University of Maryland College Park, USA & National Institute for Standards and Technology, USA Nicola Guarino, Institute of Cognitive Sciences and Technologies, CNR, Trento, Italy Patrick J. Hayes, Institute for Human and Machine Cognition, University of West Florida, USA Heinrich Herre, Institute of Informatics, University of Leipzig , Germany Jacques Jayez, ENS-Humanities, Lyon, France Ingvar Johansson, Institute for Formal Ontology and Medical Information Science, University of Leipzig, Germany Hannu Kangassalo, Dept of Computer and Information Sciences, University of Tampere, Finland Fritz Lehmann, USA Leonardo Lesmo, Dept of Computer Science, University of Torino, Italy Bernardo Magnini, Centre for Scientific and Technological Research, ITC, Trento, Italy David Mark, Dept of Geography, State University of New York, Buffalo, USA William E. McCarthy, Department of Accounting, Michigan State University, USA Robert Meersman, Dept of Computer Science, Free University of Brussels, Belgium Chris Menzel, Dept of Philosophy, Texas A&M University, USA Friederike Moltmann, Dept of Philosophy, Stirling University, UK Philippe Muller, Research Institute for Computer Science, University of Toulouse III, France John Mylopoulos, Dept of Computer Science, University of Toronto, Canada Leo Obrst, MITRE, USA Massimo Poesio, Dept of Computer Science, University of Essex, UK Ian Pratt-Hartmann, Dept of Computer Science, University of Manchester, UK James Pustejovsky, Dept of Computer Science, Brandeis University, USA Steffen Schulze-Kremer, German Resource Center for Genome Research, Berlin, Germany Peter Simons, School of Philosophy, University of Leeds, UK Barry Smith, Dept of Philosophy, State University of New York, Buffalo, USA & Institute for Formal Ontology and Medical Information Science, University of Leipzig, Germany John Sowa, USA Veda Storey, Dept of Computer Information Systems, Georgia State University, USA Mike Uschold, The Boeing Company, USA Achille Varzi, Dept of Philosophy, Columbia University, USA Laure Vieu, Research Institute for Computer Science, CNRS, Toulouse, France Yair Wand, Management Information Systems Division, University of British Columbia, Vancouver, Canada Chris Welty, IBM Watson Research Center, USA Roel Wieringa, Computer Science Department, University of Twente, The Netherlands ==== ------------------------------------------------------------------------- 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 Fri Mar 5 16:59:04 2004 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Fri, 5 Mar 2004 17:59:04 +0100 Subject: Appel: Workshop on Robust Methods in Analysis of Natural Language Data, COLING'2004 Message-ID: Date: Thu, 4 Mar 2004 18:30:46 -0100 (MET) From: Message-ID: <38790.193.49.161.187.1078421446.squirrel at www.loria.fr> X-url: http://lithwww.epfl.ch/romand2004/ X-url: http://www.issco.unige.ch/coling2004/), X-url: http://lithwww.epfl.ch/romand2004/ Call For Papers [Submission Deadline: March, 31st 2004] ROMAND 2004 3rdÊ workshop on RObust Methods in Analysis of Natural language Data A satellite event of COLING 2004 Geneva - August 29th 2004 http://lithwww.epfl.ch/romand2004/ Robustness in Computational Linguistics has been recently recognized as a central issue for the design of interactive applications based on natural language communication. If a failure of the system can be acceptable in batch applications requiring a human intervention, an on-line system should be capable of dealing with unforeseen situations in a more flexible way. When we talk about system failure we do not think at inherent program failures like infinite loops or system exception, we consider, rather, failures related to the processing of the input and its assimilation in the system's knowledge base. A failure of this kind means simply that the system does not "understand" the input. The automated analysis of natural language data has become a central issue in the design of Intelligent Information Systems. Processing unconstrained natural language data is still considered an AI-hard task. However, various analysis techniques have been proposed in order to address specific aspects of natural language. In particular, recent interest has been focused on providing approximate analysis techniques, assuming that when perfect analysis is not possible, partial results may be still very useful. ROMAND 2004 is the third of a series of workshops aimed at bringing together researchers and students that work in fields like artificial intelligence, computational linguistics, human-computer interaction, cognitive science and are interested in robust methods in natural language processing and understanding. The term "natural language" is intended as all the possible modalities of human communication and it is not restricted to written or spoken language. Theoretical aspects of robustness in Natural Language Processing (NLP) and Understanding (NLU) are welcome as well as engineering and industrial experiences. We are also interested in research works that investigate different types of linguistic modules integration, in order to characterise their advantages and disadvantages with respect to different types of applications, and works that propose different types of NLP/NLU systems, ranging from sequential/pipelined architectures to more loosely-coupled multi-level distributed architectures. We invite papers on all topics related to robustness in natural language processing, including, but not limited to: Natural Language Architectures Robust Morpho-Syntactic Parsing Robust Semantics Robust Discourse Analysis Robust Computational Pragmatics Complexity of linguistic analysis Spell checking and automated spell correction NLP and Soft Computing Hybrid methods in computational linguistics Information Extraction Multimedia Document Analysis Spoken Language Understanding Multimodal Human-Computer Interfaces Cognitive Linguistics INVITED TALKS Dr. Frank Keller Ð University of Edinburgh: "Gradient Grammaticality: Applications in Robust Parsing" SUBMISSION PROCEDURE: Authors should submit an anonymous paper (avoiding, as much as possible, hints for the identification of authors) of at most 10 pages (including pictures and references), intended for talks with a duration of 20 minutes plus 10 minutes for discussions. The paper should follow the COLING formatting style available on the main conference web site (http://www.issco.unige.ch/coling2004/), and the authors must also send us a wrapper e-mail message indicating: the AUTHOR'S NAMES, AFFILIATION, ADDRESS, and E-MAIL address of (at least) the contacting author, an ABSTRACT of the submitted paper (less than 500 words), a list of KEYWORDS (no more than 5). The papers should be submitted electronically in PDF (preferred) or postscript format to: mailto:romand at epfl.ch. IMPORTANT DATES: Papers submission: March 31st Acceptance notification: May 7th Final version: June 4th Workshop: August 29th PROGRAM CHAIRS Vincenzo Pallotta (Swiss Federal Institute of Technology - Lausanne, International Computer Science Institute - Berkeley) Amalia Todirascu (University of Troyes and University of Iasi) PROGRAM COMMITTEE Afzal Ballim Alberto Lavelli Alexander Clark Atro Voutilainen Bangalore Srinivas C.J. Rupp Dan Cristea Diego Molle-Aliod Eric Wherli Jose Iria Fabio Massimo Zanzotto Fabio Rinaldi Frank Keller Giovanni Coray GŸnther Gšrz Hatem Ghorbel Jean-Cédric Chappelier Jean-Pierre Chanod Joachim Niehren John Carroll Kay-Uwe Carstensen Manuela Boros Maria Teresa Pazienza Martin Rajman Michael Hess Patrick Ruch Roberto Basili Rodolfo Delmonte Salah Ait-Mokhtar Susan Armstrong Wolfgang Menzel Yuji Matsumoto LOCAL ORGANIZATION Violeta Seretan (University of Geneva) Hatem Ghorbel (Swiss Federal Institute of Technology - Lausanne) CONTACT INFORMATION: All inquiries should be sent to [romand at epfl.ch]. Please note that general organizational details (registration, accommodation, etc.) are taken care of by COLING 2004, not by the workshop organizers. More information are available the workshop's Web page at http://lithwww.epfl.ch/romand2004/ ------------------------------------------------------------------------- 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 Fri Mar 5 16:59:37 2004 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Fri, 5 Mar 2004 17:59:37 +0100 Subject: Appel: SIGdial04, Demos Message-ID: Date: Thu, 4 Mar 2004 17:06:09 +0100 From: Michael Strube Message-ID: <16455.21489.798775.624253 at eml.villa-bosch.de> X-url: http://sigdial04.eml-research.de ____________________________________________________________________________ Call for Demos 5th SIGdial Workshop on Discourse and Dialogue Cambridge/MA, April 30 and May 1, 2004 (immediately preceding HLT-NAACL) ____________________________________________________________________________ As part of SIGDIAL 04 (http://sigdial04.eml-research.de), we solicit demo presentations of speech and/or natural language systems with discourse or dialog/conversation capabilities. We welcome researchers who wish to present demos using discourse and dialogue in a wide range of efforts (including, for example, corpora annotation, reference resolution systems, discourse act parser, tutorial systems, embodied conversational characters, meeting room agents, spoken language agents interacting via telephone, help agents, humanoid robots conversing with people, etc.). Submission of a 1-2 page description of the demo is required. Submission format: Submissions must be electronic in PDF format and should follow the format of ACL proceedings (except that SIGdial04 demo submissions should include author information since reviewing will not be blind). Authors are strongly encouraged to use the LaTeX style files or MSWord equivalents available on the HLT/NAACL website. Submission procedure: A PDF file of the paper must be uploaded onto the system by March 29, 2004 via the SIGdial04 submission webpage available from http://sigdial04.eml-research.de. Authors who cannot submit a PDF file electronically should contact the program chairs in advance of the paper submission deadline. Authors will not have an opportunity to submit a revised demo description if the demo is accepted, so everyone is advised to provide a submission they consider final. Demo submitters will be notified by April 7th about acceptance of their submissions. No additional documentation will be required. The demo submissions will be collated together as a booklet and provided to all participants at the SIGDIAL '04 meeting. ------------------------------------------------------------------------- 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 Fri Mar 5 17:00:12 2004 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Fri, 5 Mar 2004 18:00:12 +0100 Subject: Appel: Linguistics Workshop on Machine Translation Message-ID: Date: Wed, 03 Mar 2004 00:25:06 +0100 From: "Sylviane CARDEY (Centre Tesnière)" Message-Id: <3.0.6.32.20040303002506.0180da70 at utinam.univ-fcomte.fr> X-url: http://tesniere.univ-fcomte.fr Appel à communications Call for papers Appel à communications aux Journées linguistiques " traduction automatique, langues contrôlées et langues de spécialités " Comité scientifique : Haytham Alsharaf (Université de Koweït) Florence Beaujard (Airbus) Xavier Blanco (Université Autonome de Barcelone, Espagne) Christophe Bogachi (Université de Varsovie, Pologne) Farouk Bouhadiba (Université de Mostaganem, Algérie) Sylviane Cardey (Université de Franche-Comté, France) Hui-Lan Chao (Institut Wenzao, Taiwan) Elisa Gavieiro-Villatte (Université de Franche-Comté, France) Yves Gentilhomme (Université de Franche-Comté, France) Peter Greenfield (Université de Franche-Comté, France) Kyoko Kuroda (Shimane College, Japon) Stefan Langer (CIS, Université de Munich, Allemagne) Igor Mel'cuk (Université de Montréal, Canada) Ruslan Mitkov (Université de Wolverhampton, Angleterre) Elisabeth Ranchhod (Université de Lisbonne, Portugal) Laurent.Spaggiari (Airbus France) Comité d'organisation : Sylviane Cardey, Peter Greenfield, Séverine Vienney (Centre Tesnière), Université de Franche-Comté, France. Lieu de la manifestation Besançon, France Date 5-7 mai 2004 Programme prospectif Le programme se composera de 3 grandes sessions Traduction automatique Problèmes Théories Modèles Outils Applications et démonstrations Langues contrôlées Théories Modèles Applications Langues de spécialités Langues de spécialités/langues générales Description Problèmes Les articles devront s'inscrire dans la problématique de l'un ou de plusieurs des thèmes ci-dessus. Un résumé d'une page (caractère 12, interligne 1,5) rédigé en anglais ou en français devra parvenir à ctesniere at univ-fcomte.fr pour le 27 mars 2004 La notification d'acceptation parviendra le 5 avril 2004. Les articles en anglais ou en français devront parvenir pour le 1er septembre 2004 et seront publiés dans les actes du colloque (le format sera spécifié ultérieurement). Call for papers Linguistics Workshop on Machine Translation, Controlled Languages and Specialised Languages Venue: Besançon, France Dates: 5-7 May 2004 Scientific Committee: Haytham Alsharaf (Kuwait University) Florence Beaujard (Airbus) Xavier Blanco (Autonomous University of Barcelona, Spain) Christophe Bogachi (University of Warsaw, Poland) Farouk Bouhadiba (University of Mostaganem, Algeria) Sylviane Cardey (University of Franche-Comté, France) Hui-Lan Chao (Wenzao Institute, Taiwan) Elisa Gavieiro-Villatte (University of Franche-Comté, France) Yves Gentilhomme (University of Franche-Comté, France) Peter Greenfield (University of Franche-Comté, France) Kyoko Kuroda (Shimane College, Japan) Stefan Langer (CIS, University of Munich, Germany) Igor Mel'cuk (University of Montréal, Canada) Ruslan Mitkov (University of Wolverhampton, England) Elisabeth Ranchhod (University of Lisbon, Portugal) Laurent.Spaggiari (Airbus France) Programme Committee: Sylviane Cardey, Peter Greenfield, Séverine Vienney (Centre Tesnière), University of Franche-Comté, Besançon, France Intended Programme The programme will comprise three principal sessions: Machine Translation Problems Theories Models Tools Applications and demonstrations Controlled Languages Theories Models Applications Speciality Languages Speciality languages /general languages Description Problems The papers ought to address one or more of the above themes. A one page abstract (font size 12 point, interline 1.5) in either English or French should be emailed to: ctesniere at univ-fcomte.fr by 27 March 2004. Notification of acceptance: 5 April 2004. Accepted papers, in English or French, should be received by 1st September 2004 and will be published in the workshop's proceedings (the format will be specified later). ----------------------------------------------------------------- Professeur Sylviane CARDEY Directrice du Centre de recherche en linguistique Lucien Tesniere Faculte des Lettres, Email : sylviane.cardey at univ-fcomte.fr 30, rue Megevand, Tel: +33 (0)3 81 66 53 94 25030 BESANCON Cedex, Fax: +33 (0)3 81 66 53 00 FRANCE http://tesniere.univ-fcomte.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 thierry.hamon at LIPN.UNIV-PARIS13.FR Tue Mar 9 12:04:39 2004 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Tue, 9 Mar 2004 13:04:39 +0100 Subject: Appel: AMTA-2004 Message-ID: Date: Tue, 9 Mar 2004 00:40:29 +0100 From: Jeff Allen Message-ID: <1078789228.404d046d01d32 at imp3-q.free.fr> X-url: http://www.amtaweb.org/AMTA2004/ X-url: http://www.amtaweb.org/AMTA2004/ X-url: http://www.geocities.com/jeffallenpubs/ X-url: http://www.multilingual.com/machineTranslation62.htm X-url: http://www-lipn.univ-paris13.fr/~hamon/ First Call for Papers and Proposals AMTA-2004 - The 6th Biennial Conference of the Association for Machine Translation in the Americas Location: Georgetown University, Washington DC, USA Dates: September 28 - October 2, 2004 http://www.amtaweb.org/AMTA2004/ Theme: From Real Users to Research Introduction: The previous conference in this series (AMTA 2002) took up the theme "From Research to Real Users" which asked participants to explore why the research conducted on machine translation doesn’t seem to be moving to the marketplace. The past two years have seen the beginnings of change in this, as some research groups with data-driven translation systems are commercializing their work, and rule-based machine translation systems are introducing data-driven techniques to the mix in their products. For this conference, we reverse the question, and take as our theme user needs and explore how or whether market requirements are feeding into research programs. Issues to be addressed: * system customizability, memory requirements, and other issues affecting commercial adoption * integration and customization work * general advances in quality (including: inherent limits on achievable quality? and varying quality by application?) * How are people using MT today? The conference will host the following: * Conference papers (five categories of papers): 1. Research papers 2. MT Users Session 3. MT Research and Deployment Showcase 4. Evolution of Machine Translation 5. System Descriptions/Demonstrations * Tutorials * Roundtable/Panel Sessions * Workshops * Product Exhibition Important Dates: March 30 2004: Submission intention deadline for conference papers (abstract of maximum of 200 words + title + category + author(s) name) April 23 2004: Submission deadline for roundtable/panel sessions Submission deadline for tutorial proposals Submission deadline for technical papers and presentations Submission deadline for workshop proposals May 15 2004: Submission deadline for end user papers and presentations June 11 2004: Notification to authors July 2 2004: Camera-ready copy due July 23 2004: Final papers to publisher All conference details available at: http://www.amtaweb.org/AMTA2004/ Regards, Jeff Allen ******************************************************** Jeff Allen Advisory Board MultiLingual Computing & Technology magazine jeff at multilingual.com or jeff.allen at free.fr New web portal with MT and controlled language publications http://www.geocities.com/jeffallenpubs/ Special supplement of MultiLingual Computing & Technology focused on Machine Translation: http://www.multilingual.com/machineTranslation62.htm ******************************************************** ------------------------------------------------------------------------- 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 Mar 12 12:22:52 2004 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Fri, 12 Mar 2004 13:22:52 +0100 Subject: Conf: EURALEX 2004 Message-ID: Les inscriptions sont maintenat ouvertes pour EURALEX 2004 sur le site : http://www.univ-ubs.fr/euralex2004. EURALEX 2004 Le 11ème congrès international d'EURALEX aura lieu à Lorient, France, du 6 au 10 juillet 2004. L'organisateur est la Faculté de Lettres et Sciences Humaines de l'Université de Bretagne Sud, Lorient. La venue sera le Paquebot, le bâtiment principale de l'Université. Contact address Organisateurs du Congrès EURALEX 2004 Dr. Geoffrey Williams Faculté de Lettres et de Sciences Humaines 4 rue Jean Zay B.P. 92116 56321 Lorient cedex France Téléphone : (33) 2 97 87 65 31 Fax : (33) 2 97 87 65 25 Email : elx2004 at univ-ubs.fr Website : http://www.univ-ubs.fr/euralex2004 Les renseignements Les informations sur l'hébergement, les inscriptions et le transport seront tenues à jour sur ce site. LE CONGRES Le congrès EURALEX réunit lexicographes professionnels, éditeurs, chercheurs, universitaires, et toute personne intéressés par les dictionnaires de tous types. Le programme comprendra des conférences plénières, des sessions parallèles sur les thèmes énumérés ci-dessous, des démonstrations de logiciels, une exposition de livres et de logiciels, et des activités de détente pour les participants et leurs invités. Les thèmes suivants qui sont au centre du congrès : 1. Lexicographie et Lexicologie Computationnelle 2. Processus d'élaboration des dictionnaires 3. Rapports sur des projets lexicographiques et lexicologiques 4. Lexicographie Bilingue 5. Lexicographie pour Langues de Spécialité Terminologie et Terminographie 6. Lexicographie historique et savante et Étymologie 7. Utilisation des dictionnaires 8. Phraséologie et Collocation 9. Questions lexicologiques ayant une pertinence lexicographique 10. Autres thèmes Les conférences plénières seront · Professor John Sinclair, Tuscan Word Centre · Dr Pierre Corbin, University of Lille III · Dr Anthony Cowie, University of Leeds · Dr Christine Jacquet-Pfau, College de France Le pré-programme sera publié bientôt sur le site web. ------------------------------------------------------------------------- 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 Mar 12 12:23:39 2004 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Fri, 12 Mar 2004 13:23:39 +0100 Subject: Appel: ACL workshop : Text Summarization Branches Out Message-ID: Our apologies for multiple postings ------------------------------------------------------------------------ Text Summarization Branches Out July 25-26, 2004. Workshop at ACL 2004 42nd Annual Meeting of the Association for Computational Linguistics Forum Convention Centre Barcelona, Spain http://www.law.kuleuven.ac.be/icri/conferences/acl_summarization2004.php ------------------------------------------------------------------------ Second call for papers Text summarization is still largely in a research phase, and has so far focused on news text, but it is increasingly becoming a tool for information search and selection in a variety of media. For example, summarizing is a necessity when showing content on the screen of a mobile device. Texts integrated in multimedia documents have different genres or types, but they all require the same flexibility in the presentation of summaries by allowing parameterized compression rates and integration in a mixed media format. Text summarization has been so far dominated by statistical techniques. However, for improved output quality and increased compression, other techniques are expected to play important roles as well. Linguistically motivated natural language processing techniques, including semantic analysis and discourse analysis, are almost certainly required for summarization in non-news genres. Automated reasoning techniques could allow fusion and understanding of content. Machine learning, both supervised and unsupervised, still has a major role to play. Finally, evaluation is an ongoing concern. The proposed workshop aims to address all these issues. We invite submission of papers about text summarization including, but not limited to, the following topics. * Single-sentence compression * Multiple-sentence compression and information fusion * Domain-oriented summarization of multiple texts * Comparative summarization of multiple reviews * Summarization of Web pages * Summarization of dialogue (e.g., blogs, video captions) * Summarization of speech * Summarization for mobile devices * Summarization for other disciplines, e.g., legal or medical applications * Toward summarizing large, loosely structured texts (e.g., novels) * Temporal and event semantics for summarization * Data search structures for summaries of flexible and mixed media format * Automated and manual summary evaluation methods * Quantifying summary quality The workshop will feature an invited speaker (to be confirmed), and two panels, one looking back and one looking far ahead, plus ad-hoc discussion groups. Important Dates * Paper submission deadline: March 25, 2004 * Notification of acceptance for papers: April 25, 2004 * Camera ready papers due: May 15, 2004 * Workshop date: July 25-26, 2004 Submission Procedure Authors should submit full papers of maximum 8 pages, including references and figures, following the main conference ACL style format. Submissions should be sent to: http://www.law.kuleuven.ac.be/icri/cyber-chair/html/submit/ Organizing Committee * Eduard Hovy, Information Sciences Institute, University of Southern California, USA * Marie-Francine Moens (co-chair), Interdisciplinary Centre for Law & Information Technology, Katholieke Universiteit Leuven, Belgium * Dragomir Radev, School of Information and Department of Electrical Engineering and Computer Science, University of Michigan, USA * Stan Szpakowicz (co-chair), School of Information Technology and Engineering, University of Ottawa, Canada Program Committee * Regina Barzilay, Computer Science and Artificial Intelligence Lab, MIT, USA * Hercules Dalianis, Royal Institute of Technology, Sweden * Chiori Hori, NTT, Japan * Eduard Hovy, Information Sciences Institute, University of Southern California, USA * Hongyan Jing, IBM T.J. Watson Research Center, USA * Kathy McKeown, Computer Science Department, Columbia University, USA * Chin-Yew Lin, Information Sciences Institute, University of Southern California, USA * Inderjeet Mani, Department of Linguistics, Georgetown University, USA * Daniel Marcu, Information Sciences Institute, University of Southern California, USA * Marie-Francine Moens, Interdisciplinary Centre for Law & Information Technology, Katholieke Universiteit Leuven, Belgium * Dragomir Radev, School of Information and Department of Electrical Engineering and Computer Science, University of Michigan, USA * Horacio Rodriguez, Departamento de LSI, Universitat Politecnica de Catalunya, Spain * Horacio Saggion, Department of Computer Science, University of Sheffield, UK * Judith Schlesinger, IDA/Center for Computing Sciences, USA * Karen Sparck Jones, Computer Laboratory, University of Cambridge, UK * Stan Szpakowicz, School of Information Technology and Engineering, University of Ottawa, Canada * John Tait, School of Computing and Technology, University of Sunderland, UK * Simone Teufel, Computer Laboratory, University of Cambridge, UK * Peter Turney, NRC Ottawa, Canada * Hans van Halteren, Department of Language and Speech, University of Nijmegen, The Netherlands Contact addresses Marie-Francine Moens Interdisciplinary Centre for Law & Information Technology Katholieke Universiteit Leuven Tiensestraat 41 B-3000 Leuven Belgium marie-france.moens at law.kuleuven.ac.be http://www.law.kuleuven.ac.be/icri/staff/staff.php?id=13 Stan Szpakowicz School of Information Technology and Engineering University of Ottawa 800 King Edward Avenue Ottawa, Ontario K1N 6N5 Canada szpak at site.uottawa.ca http://www.site.uottawa.ca/~szpak ------------------------------------------------------------------------- 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 Mar 12 12:24:28 2004 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Fri, 12 Mar 2004 13:24:28 +0100 Subject: Ecole: University of Geneva : School of Translation and Interpretation Message-ID: Dear colleagues, The School of Translation and Interpretation at the University of Geneva delivers three postgraduate degrees in multilingual information processing and terminology. These postgraduate programs (in French), are aimed mainly at translators and interpreters who would like to take advantage of recent advances in multilingual IT. Details are appended below. Please distribute this announcement to concerned people, especially students. A poster (in French) is also available at http://www.unige.ch/eti/courstim/unige-eti-postgrade.pdf With my best regards, Prof. Margaret King, Head of the Multilingual Information Processing Departement ______Description of the postgraduate programs _______ The School of Translation and Interpretation at the University of Geneva delivers three postgraduate degrees in multilingual information processing and terminology: two DESS (diplômes d'études supérieures spécialisées) and one DEA (diplôme d'études approfondies). The courses are listed below, in French. The DESS requires at least four modules, followed by an internship period and a DESS thesis. The DEA requires seven modules, followed by a research period, and the writing and defense of a DEA thesis, which may lead to a doctorate. DEA en traitement informatique multilingue (TIM) - Introduction à la description formelle des langues - Traitement informatique multilingue - Introduction à la programmation linguistique - Traitement informatique des textes - Fondements théoriques de la terminologie DESS en terminologie - Principes généraux et méthodologie de la terminologie - Pratique de la terminologie (I et II) - Terminologie et informatique DESS en traduction assistée par ordinateur (TAO) - Technologies de l'information et de la communication - Traductique - Technologies de pointe - Traduction automatique - XML pour le traitement informatique multilingue Registration: Applications must be made before March 31, 2004. The procedure is described on the ETI website at http://www.unige.ch/eti (follow 'Admission', then 'DEA/DESS/doctorat'). For more information Please contact Mrs. Doris Schmidt Fourmont, senior student advisor (Doris.Schmidt at eti.unige.ch or +41 22 379 87 07), or see the ETI website at 'Formations' and 'Règlement d'études'. ------------------------------------------------------------------------- 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 Mar 12 12:25:09 2004 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Fri, 12 Mar 2004 13:25:09 +0100 Subject: =?ISO-8859-1?Q?ATALA=3A_journee_du_05/06_=3A_Le_trai?= =?ISO-8859-1?Q?tement_automatique_des_nouvelles_formes_de_co?= =?ISO-8859-1?Q?mmunication_=E9crite?= Message-ID: Journée d'Etude de l'ATALA ========================== Le traitement automatique des nouvelles formes de communication écrite (e-mails, forums, chats, SMS, etc.) Organisateurs ------------- Emilie Guimier De Neef (France Telecom R & D) Jean Véronis (Université de Provence) Conférencier invité ------------------- Jacques Anis, Université Paris X Date ---- 5 juin 2004 Lieu ---- ENST, 46, rue Barrault ou 49, rue Vergnault, 75013 Paris Métro : Corvisart Thème ----- Depuis quelques années on assiste à une véritable explosion de nouvelles formes de communication écrite (NFCE) : e-mails, forums, chats, SMS, etc. Le développement de passerelles entre les différents médias (les e-mails et les SMS s'écoutent) ainsi que la nécessité de faciliter la gestion des contenus (classification automatique des e-mails, recherche d'informations...) amènent de plus en plus de technologies du TAL à s'appliquer aux NFCE : synthèse de la parole, filtrage et classification automatique, détection automatique de mots-clés et de thèmes, traduction automatique, etc. Or, les NFCE montrent une grande déviance par rapport à l'écrit plus ou moins normé que le TAL a l'habitude de traiter. Si on laisse de côté les problèmes de composition posés par les e-mails (renvois successifs, complétion progressive des messages) pour ne conserver que les aspects proprement linguistiques posés par les NFCE, on observe d'une part des phénomènes que l'on pourrait regrouper sous le terme de "ratés" (erreurs orthographiques et typographiques, absence de séparateur entre les mots etc.) qui doivent leur origine au mode de communication souvent direct ou semi-direct, à la rapidité de composition du message ou aux contraintes de saisies imposées par le clavier utilisé (terminal mobile)... Mais on constate d'autre part une véritable émergence de nouveaux modes d'écriture (abréviations, smileys, écriture "texto", etc.), au milieu d'une très grande variabilité et d'une créativité constante. Ce qui semble caractéristique des NFCE, c'est que les utilisateurs inventent en permanence de nouveaux procédés. Enfin, des caractéristiques fortement dialogiques rendent les NFCE intermédiaires d'une certaine façon entre l'écrit "classique" et l'oral : les e-mails se citent, les chats conversent. Paradoxalement, on note peu de publications en TAL sur le sujet, qui a surtout été abordé sous l'angle de la sociologie et de la communication. Les difficultés qui se posent aux systèmes de TAL sont immenses, même pour ceux qui ont atteint une certaine maturité sur l'écrit classique (étiqueteurs morpho-syntaxiques, etc.). Elles aboutissent le plus souvent à une dégradation considérable des performances, rendant souvent leur utilisation presque impossible en pratique. Le but de la journée est de réunir des chercheurs autour des problèmes liés au traitement linguistique des nouvelles formes de communication écrite : - ponctuation absente ou exagérément utilisée - typographie déviante - erreurs orthographiques massives - mode de création des abréviations - phonétisation de l'écriture - nouvelles marques d'expressivité et d'émotion - aspects dialogiques - différences linguistiques profondes (usage des temps, etc.) Cette liste n'est pas limitative. Soumission ---------- Un résumé de deux à quatre pages doit être envoyé avant le 5 mai 2004 par courrier électronique, en format RTF ou TXT uniquement à Emilie Guimier De Neef ou Jean Véronis Les notifications d'acceptation seront envoyées le 15 mai 2004. Pour plus d'informations sur l'ATALA et sur l'organisation des journées d'études, consultez le site de l'ATALA à l'adresse : http://www.atala.org ------------------------------------------------------------------------- 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 Mar 12 12:31:46 2004 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Fri, 12 Mar 2004 13:31:46 +0100 Subject: Conf : Controlled Language seminar at the Society for Technical Communication Message-ID: Controlled Language seminar at the Society for Technical Communication (STC) France Chapter meeting. Date: 2 April 2004 Location: Holiday Inn Hotel, Paris, France, 19th arrondissement. Invited speakers: Jeff Allen (Mycom France and MultiLingual Computing & Technology) Kathy Barthe (Airbus) More information and registration form available in the "Controlled Language and Machine Translation Events" section at: http://www.geocities.com/controlledlanguage/ Regards, Jeff ******************************************************** Jeff Allen Advisory Board MultiLingual Computing & Technology magazine jeff at multilingual.com or jeff.allen at free.fr New web portal (including MT and CL publications) http://www.geocities.com/jeffallenpubs/ ******************************************************** ------------------------------------------------------------------------- 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 Thu Mar 18 07:35:42 2004 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Thu, 18 Mar 2004 08:35:42 +0100 Subject: ATALA: journee du 15/05 : Evaluation et analyseurs syntaxiques Message-ID: Samedi 15 mai 2004 EVANS :"'Évaluation et analyseurs syntaxiques" Journée organisée par Patrick Paroubek , Isabelle Robba et Anne Vilnat(LIMSI - CNRS) Appel à contribution Depuis une dizaine d'années, avec l'apparition des outils de recherche d'information sur le web, de nouvelles techniques d'analyse syntaxique plus robustes ont vu le jour. Les analyseurs partiels construisent une analyse parfois minimale, incomplète, mais cela quels que soient lataille et le contenu des données à traiter. Dans le même temps, les analyseurs qui tentent de produire systématiquement une analyse "complète", ou la plus complète possible ont continué d'améliorer leurs résultats. Pour aider au développement de ces analyseurs, mais aussi pour permettre la comparaison de leurs performances, il est important de disposer des méthodes et des outils permettant de les évaluer. Et la mise en oeuvre de ces méthodes suppose plusieurs étapes qui sont: * la définition d'un format d'annotation permettant une large couverture des phénomènes syntaxiques ; * le choix d'un corpus et son annotation manuelle (ou semi-automatique) dans ce format d'annotation ; * la définition d'un ensemble de mesures permettant l'évaluation ; * la mise au point des outils aussi bien d'annotation, que de transcription et d'évaluation. De nombreux pays ont commencé à s'intéresser à l'évaluation. Des discussions ont eu lieu sur les annotations à produire, sur les méthodes pour les obtenir et des corpus annotés dans différentes langues ont été peu à peu constitués : que ce soit en anglais (voir le célèbre Penn TreeBank et sa "dernière" couche le Propbank) mais aussi et peut-être surtout dans un certain nombre de langues à moins forte diffusion, comme le bulgare (BulTreeBank), le tchèque (PDT), le norvégien, le suédois, le finlandais, le danois (Arboretum), le catalan, le basque et l'espagnol (3LB), l'allemand (Negra, TéBa-D). En ce qui concerne l'anglais, qui est sans doute la langue pour laquelle les recherches étaient les plus avancées, les métriques et les corpus annotés dans le cadre de la campagne PARSEVAL sont aujourd'hui remis en cause car ils ne sont ouverts ni à d'autres langues ni à de nouveaux formats d'analyse (voir l'atelier de la conférence LREC 2002 : Beyond Parseval towards improved evaluation measures for parsing systems). Ce qui nous montre que la problématique de l'évaluation des analyseurs syntaxiques n'est en rien résolue et donc est ouverte à toute nouvelle proposition. Pour le français, la campagne d'évaluation EVALDA/EASY du programme Technolangue, à l'initiative du ministère délégué à la recherche et aux nouvelles technologies) a débuté en janvier 2003. Elle sert de lieu d'expérimentation pour tester de nouvelles approches pour l'évaluation des analyseurs syntaxiques du français. Le but de cette journée sera donc de développer une réflexion autour des méthodologies d'évaluation, des corpus, des métriques, des outils et des formalismes d'annotation. Conférencier invité: John Carroll, de l'Université du Sussex, donnera une conférence invitée lors de cette journée : "Evaluating parsers using decomposed and weighted representations" Les contributions attendues pourront porter sur l'un des thèmes suivants : * l'annotation des corpus (formalisme, outils, ...) * les corpus * les méthodologies d'évaluation * les métriques d'évaluation (choix, outils ...) * les outils de projection d'un analyseur dans un formalisme Des articles prospectifs sur l'évaluation et les analyseurs syntaxiques seront également les bienvenus. Organisateurs : Patrick Paroubek, Isabelle Robba et Anne Vilnat Format des soumissions : Résumés longs ou articles courts entre 2 et 4 pages. Les soumissions devront se faire sous format électronique de préférence, en version pdf, ou ps. Les résumés devront être envoyés à : evans at limsi.fr. En cas de problème, vous pouvez également transmettre une version papier, adressée aux organisateurs, au : LIMSI, BP133, 91403 Orsay Cedex Comité Scientifique * Veronique Gendner (LIMSI-CNRS) * Laura Monceaux (LINA - Univ. Nantes) * Patrick Paroubek (LIMSI-CNRS) * Isabelle Robba (LIMSI-CNRS) * Anne Vilnat (LIMSI-CNRS) * Salah Ait-Mokhtar (XRCE-XEROX) Calendrier: * 13/04/04 - date limite pour la soummission des articles * 30/04/04 - notification aux auteur * 15/05/04 - journee Pour plus d'informations sur l'ATALA et sur l'organisation des journées d'études, consultez le site de l'ATALA à l'adresse : http://www.atala.org ou le site de la journee http://www.limsi.fr/Recherche/CORVAL/atala_evans ------------------------------------------------------------------------- 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 Thu Mar 18 07:35:47 2004 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Thu, 18 Mar 2004 08:35:47 +0100 Subject: Conf: 5th SIGdial Workshop on Discourse and Dialogue Message-ID: ____________________________________________________________________________ SIGdial '04 News 5th SIGdial Workshop on Discourse and Dialogue Cambridge/MA, April 30 and May 1, 2004 (immediately preceding HLT-NAACL) ____________________________________________________________________________ PROGRAM The program for the SIGdial '04 workshop is available on the SIGdial '04 homepage (http://sigdial04.eml-research.de). Follow the link to "Program". ____________________________________________________________________________ CALL FOR DEMOS The deadline for demo submissions is March 29, 2004. We solicit demo presentations of speech and/or natural language systems with discourse or dialog/conversation capabilities. We welcome researchers who wish to present demos using discourse and dialogue in a wide range of efforts (including, for example, corpora annotation, reference resolution systems, discourse act parser, tutorial systems, embodied conversational characters, meeting room agents, spoken language agents interacting via telephone, help agents, humanoid robots conversing with people, etc.). See http://sigdial04.eml-research.de and follow the link to "Call for Demos". ____________________________________________________________________________ REGISTRATION Online registration for SIGdial '04 is available on the HLT/NAACL website (http://www.aclweb.org/hltnaacl04reg/hltnaacl04reg.php). ____________________________________________________________________________ STUDENT VOLUNTEEERS We are looking for student volunteers who would help at the registration desk (among other duties) in exchange for free registration. This is not a full-time job but you may miss a session or two. Please don't register but contact us at sigdial04 at eml-research.de. ------------------------------------------------------------------------- Message diffus� par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://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 Thu Mar 18 07:35:50 2004 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Thu, 18 Mar 2004 08:35:50 +0100 Subject: Conf: Text Summarization Branches Out : DEADLINE CHANGES Message-ID: [A new paper submission deadline -- apologies for reposting.] Text Summarization Branches Out Workshop at the 42nd Annual Meeting of the Association for Computational Linguistics Forum Convention Centre, Barcelona, Spain July 25-26, 2004 http://www.law.kuleuven.ac.be/icri/conferences/acl_summarization2004.php ---------------- The announcement posted on March 12 asked for submissions by March 25, 2004. The new dates are as follows: * Paper submission deadline: April 1, 2004 * Notification of acceptance: April 25, 2004 * Camera-ready papers due: May 15, 2004 ------------------------------------------------------------------------- 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 Thu Mar 18 07:35:54 2004 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Thu, 18 Mar 2004 08:35:54 +0100 Subject: Ecole: linguistique de corpus: constitution, archivage, evaluation Message-ID: ECOLE Thématique linguistique de corpus: constitution, archivage, évaluation Lieu : Université de Caen, campus 2, Département d'informatique Dates : 14-19 juin 2004 Durée : 6 jours Nombre total de participants : 56 Hébergement en cité universitaire SITE DE L'ECOLE THEMATIQUE : http://www.crisco.unicaen.fr/ELC IMPORTANT: DATE LIMITE DE DEPOT DES CANDIDATURES LE 30 AVRIL 2004 (voir fiche d'inscription sur le site) PUBLIC CONCERNE : Les chercheurs du département SHS et du département STIC (domaine IHM) du CNRS ainsi que les enseignants-chercheurs et doctorants en linguistique théorique et appliquée. THEME : Présentation et manipulation des méthodes et outils qui permettent la recherche et l'analyse critique de données linguistiques tant à l'oral qu'à l'écrit avec l'aide des technologies de l'information. SITUATION SCIENTIFIQUE : Le développement de la linguistique de corpus ne cesse de croître depuis les années 1990 (ressources informatisées volumineuses, essor des ouvrages sur la linguistique de corpus, création récente de l'ILF, intégration des cours de linguistique de corpus dans les formations universitaires). Parallèlement, le dialogue entre informaticiens et linguistes reste frileux. Un décloisonnement de ces disciplines s'avère fondamentalement nécessaire. Cette Ecole sera conduite dans un cadre interdisciplinaire où se côtoieront principalement informaticiens, ingénieurs, linguistes et juristes. CONSÉQUENCES ATTENDUES : Développer une synergie en linguistique de corpus au sein des laboratoires des participants, doter les chercheurs en linguistique théoriques d?un réelle autonomie, partager les expériences et connaître les besoins spécifiques des laboratoires. GRANDS AXES DU PROGRAMME : Aspects théoriques et méthodologiques des corpus (constitution, corpus de référence, corpus communs, méta-données, codage, métrique). Aspects pratiques (création et archivage, enrichissements, outils de requêtes et de calcul). MODALITES PEDAGOGIQUES : Alternance de cours théoriques et de situations pratiques. MOTS CLES : LINGUISTIQUE CORPUS TIC (Techniques d'Information et de Communication) ARCHIVAGE Inscriptions 100 euros 45 euros pour les étudiants gratuit pour les agents CNRS Responsable scientifique Anne LACHERET-DUJOUR, Université de Caen TEl. : 02 31 56 56 27 - Fax : 02 31 56 54 27 - E mail : anne.lacheret at crisco.unicaaen.fr Responsable régional du projet pour la formation permanente: Emmanuel Mettereau Délégation Régionale : Normandie TEL : 02 31 43 45 37 - Fax 02 31 43 45 06 E mail : meterreau at dr19.cnrs.fr Comité scientifique Catherine Camugli-Gallardo CRISCO Jacques François CRISCO Benoît Habert LIMSI Anne Lacheret-Dujour CRISCO Thomas Lebarbé LIDILEM Franck Neveu CRISCO Anne Nicolle GREYC Laurent Romary LORIA Comité d'organisation Catherine Camugli-Gallardo CRISCO Jacques François CRISCO Anne Lacheret-Dujour CRISCO Thomas Lebarbé GREYC Sébastien Monnier CRISCO Anne Nicolle GREYC Emmanuel Meterreau Délégation Normandie ------------------------------------------------------------------------- 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 Thu Mar 18 07:36:02 2004 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Thu, 18 Mar 2004 08:36:02 +0100 Subject: Jobs: Research Positions in Tarragona Message-ID: 2 Research Positions at the Research Group on Mathematical Linguistics, Rovira i Virgili University, Tarragona, Spain Funded by the Spanish Ministry for Science and Technology and Rovira i Virgili University Position 1: for scholars having up to 10 years of postdoc experience Position 2: for scholars having up to 3 years of postdoc experience Duration: 5 year-contract starting in Autumn 2004 Salary position 1: 30,000 euros/year (before taxes) + up to 12,000 euros for expenses (in the first two years) + full Social Security coverage Salary position 2: 23,000 euros/year (before taxes) + full Social Security coverage Research topics: formal language theory and any of its application areas Deadline position 1: March 5, 2004 Deadline position 2: March 22, 2004 Expressions of interest position 1: until February 27, 2004 Expressions of interest position 2: until March 12, 2004 Contact: cmv at astor.urv.es Website: http://pizarro.fll.urv.es/continguts/linguistica/proyecto/grlmc.htm -------------------------------------------------------------------------------------------------- Carlos Martin-Vide Head, Research Group on Mathematical Linguistics Head, Department of Romance Philologies Rovira i Virgili University Pl. Imperial Tarraco, 1 43005 Tarragona, Spain phone: +34-977559543 fax: +34-977559597 e-mail: cmv at astor.urv.es http://pizarro.fll.urv.es/continguts/linguistica/proyecto/grlmc.htm ------------------------------------------------------------------------- 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 Thu Mar 25 16:49:58 2004 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Thu, 25 Mar 2004 17:49:58 +0100 Subject: Appel: COLING Workshop : INTERNATIONAL JOINT WORKSHOP ON NLP IN BIOMEDECINE Message-ID: SECOND CALL FOR PAPERS COLING Workshop INTERNATIONAL JOINT WORKSHOP ON NATURAL LANGUAGE PROCESSING IN BIOMEDICINE AND ITS APPLICATIONS (BioNLP/NLPBA 2004) http://www.genisis.ch/~natlang/JNLPBA04/ Call for Papers http://www.genisis.ch/~natlang/JNLPBA04/cfp.html Geneva, Switzerland August 28-29, 2004 ** Regular papers deadline: 14th April ** ** Shared task paper deadline: 21st April ** Workshop Description Recent years have seen a growing interest in the application of NLP techniques to texts in the domains of biology and medicine. The problem of information overload that has resulted from the massive growth in the scientific literature has clearly shown the necessity to automatically locate, organize and manage facts relating to experimental results. At the same time clinicians have experienced greatly improved access to the medical literature and clinical repositories which needs to be matched by the development of enhanced information access tools. This year NLPBA (http://www.genisis.ch/~natlang/NLPBA02/) and BioNLP (http://www-tsujii.is.s.u-tokyo.ac.jp/ACL03/bionlp.htm) merge for a joint workshop with the aim of bringing together researchers from natural language processing, bio-informatics, medicine and ontologies who are concerned with developing methods and resources for solving these problems. Over the last five years we have seen significant steps forward in the development of language technology and large-scale resources for the Bio-Medical domain such as linguistically annotated corpora (e.g. GENIA POS and NE corpora), ontologies (e.g. Gene Ontology), thesauri (e.g. UMLS Metathesaurus), lexicons and term lists (e.g. UMLS SPECIALIST) as well as information retrieval collections (e.g. TREC Genomics track). At the application level we see development of question answering systems, event recognition, zone (rhetorical region) identification, as well as term and bio-entity recognition. The demand for information access tools from domain users is increasing to support literature survey, often integrated into online portals where scientists can navigate through related information resources such as genetics and disease databases. Ongoing challenges relate to the growing and ambiguous nomenclature, the need to integrate deep knowledge sources into machine learning, a need to scale up methods for processing full text articles etc. The objective of the workshop is to bring together researchers in this area, to establish common themes and goals between different groups. We have seen from previous experience in the natural language learning and information retrieval communities the benefits of sharing resources and developing common evaluation criteria. In this workshop we are introducing a special shared task to promote discussion of these issues as well as the objective of integrating machine learning with knowledge resources. We invite submission of papers on topics related to bio-medical NLP including, but not limited to: * Information extraction * Text mining * Named entity recognition * Coreference resolution * Term recognition * Knowledge-based information retrieval * Multi-lingual resources and applications * Ontology construction and ontology mapping * Visualization tools for viewing clustered or extracted information or meta-data * Multi-modal approaches combining text and images, etc. * Event recognition * Construction of pathways from literature and databases * Creation of data-sets of bio-medical entities, coreferences and relations * Annotation standards and quality control methodologies * Resource integration and re-engineering * Corpus/lexicon construction * Text summarization and report generation Shared Task http://research.nii.ac.jp/~collier/workshops/JNLPBA04st.htm This year we propose to have a special shared task: bio-medical named entity recognition from the GENIA corpus. The purpose of this track is essentially to investigate the integration of statistical machine learning methods with symbolic knowledge sources from the bio-medical domain such as ontologies, thesauri and lexicons : shared task description. Invited Speaker To be announced soon Paper Format and Submission Papers must follow the COLING 2004 templates, and will be submitted by email to jnlpba-submit at sim.hcuge.ch. Regular papers should follow the COLING 2004 templates for regular papers (i.e. at most 7 pages) and shared task papers should be formatted as per the COLING project notes style (4 pages) focussing in particular on method, results and discussion. Important Dates Submission deadline for regular workshop papers: April 14th, 2004 Submission deadline for shared task papers: April 21st, 2004 Notification of accepted papers: May 14th, 2004 Deadline for camera ready copies: June 6th, 2004 Workshop Chairs Nigel Collier (National Institute of Informatics, Japan) Patrick Ruch (University Hospital of Geneva and EPFL, Switzerland) Adeline Nazarenko (LIPN, France) Organizing Committee Alfonso Valencia (Centro Nacional de Biotecnologia, Spain) Carol Friedman (CUNY/Columbia University, USA) Donia Scott (University of Brighton, UK) Udo Hahn (Albert-Ludwigs University, Freiburg, Germany) Junichi Tsujii (University of Tokyo, Japan) Program Committee Sophia Ananiadou (University of Salford, UK) Alan Aronson (National Library of Medicine, USA) Robert Baud (University Hospital of Geneva, Switzerland) Christian Blaschke (CNB, Spain) Oliver Bodenreider (National Library of Medicine, USA) Berry de Bruijn (National Research Center, Canada) Marc Craven (University of Wisconsin, USA) Robert Gaizauskas (University of Sheffield, UK) Eric Gaussier (Xerox, XRCE, France) Vasileios Hatzivassiloglou (Columbia University, USA) Lynette Hirschman (MITRE, USA) Dimitar Hristovski (University of Ljubljana, Slovenia) Jerry Hobbs (USC/ISI, USA) Aravind Joshi (University of Pennsylvania, USA) Su Jian (Institute for Infocomm Research, Singapore) Asao Fujiyama (National Institute of Informatics, Japan) Arne Jonsson (University of Linkoping, Sweden) Frederique Lisacek (GeneBio SA, Switzerland) Yuji Matsumoto (NAIST, Japan) Claire Nedellec (INRA, France) Kousaku Okubo (Kyushu University, Japan) Jong C. Park (KAIST, Korea) Thierry Poibeau (LIPN, France) Denys Proux (Xerox, XRCE, France) James Pustejovsky (Brandeis University, USA) Dietrich Rebholz-Schuhmann (European Bioinformatics Institute, EU) Irena Spasic (UMIST, UK) Ben Stapley (UMIST, UK) Padmini Srinivasan (University of Iowa, USA) Hirotoshi Taira (NTT Communication Science, Japan) Toshihisa Takagi (University of Tokyo, Japan) Yuka Tateishi (University of Tokyo, Japan) Anne-Lise Veuthey (SIB, Switzerland) Limsoon Wong (Institute for Infocomm Research, Singapore) Pierre Zweigenbaum (AP-HP, INSERM & INaLCO, France) Shared Task Committee Nigel Collier (National Institute of Informatics, Japan) Jindong Kim (University of Tokyo, Japan) Yuka Tateisi (University of Tokyo, Japan) Tomoko Ohta (University of Tokyo, Japan) Yoshimasa Tsuruoka (University of Tokyo, Japan) Contact Information General organization : jnlpba-request at sim.hcuge.ch Shared task organization: bio04sharedtask at nii.ac.jp Main page : http://www.genisis.ch/~natlang/JNLPBA04/ ------------------------------------------------------------------------- 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 Thu Mar 25 17:20:39 2004 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Thu, 25 Mar 2004 18:20:39 +0100 Subject: Soft: Flemm v31 Message-ID: (Version Française) (English version : see below) ===================================================================== Flemmv31 - Analyseur morphologique Flexionnel du Français - version 3.1 Fiammetta Namer ===================================================================== FLEMMv3.1 est un ensemble de modules Perl5 qui effectue l'analyse flexionnelle des formes fléchies de textes en français qui ont été au préallable étiquetés, au moyen de l'un des deux catégorisateurs : Brill ou TreeTagger. C'est un petit programme (60kb au format zippé, à l'exclusion des programmes et corpus test), principalement basé sur l'usage de règles (un lexique de 3000 mots seulement est utilisé pour prendre en compte les exceptions). Il fonctionne sur PC ou station de travail, sous Unix, Linux ou Windows9x/NT/XP. Téléchargement : http://www.univ-nancy2.fr/pers/namer/Telecharger_Flemm.html Caractéristiques et changements par rapport à la version 3.0 : - mise à jour par rapport au nouveau jeu d'étiquettes de TreeTagger (3.1) - résultats conçus sous forme d'APIs en Perl - modules entièrement documentés (voir fonction perldoc) - traits flexionnels formatés selon les recommandations de Multext - deux modes d'affichage possibles des résultats : mode linéaire, et format XML. (Pour plus de détails, voir URL ci-dessus) ===================================================================== (English Version) ===================================================================== Flemmv31 - Inflectional morphology parser for French - version 3.1 Fiammetta Namer ===================================================================== FLEMMv3.1 is a Perl5 set of modules that performs inflectional analysis on French texts which have previously been tagged (i.e. by either the TreeTagger or the Brill tagger). This is a small program, (60kb in a zipped format, excluded the test programs and corpora) mainly rule-based (i.e. only a 3000 words lexicon is used in order to deal with exceptions). It runs on PCs or Workstation, under Unix, Linux or Windows9x/NT/XP OS. Downloading : http://www.univ-nancy2.fr/pers/namer/Telecharger_Flemm.html Charcateristics and changes wrt version 3.0 : - updating according to the new Treetagger tagset (3.1) - results designed as perl APIs - fully documented modules (see perldoc function) - inflectional features formatted according to the Multext norm. - two possible displays of the results : either linear or xml formats. (see details at the URL given above) ===================================================================== ------------------------------------------------------------------- Fiammetta NAMER Université Nancy 2 / U.F.R. Sciences Du Langage UMR 7118 "ATILF" Bureau B05 23 Boulevard Albert 1er B.P. 33 97 54000 Nancy - France Téléphone : (33) 03 83 96 71 93 URL : http://www.univ-nancy2.fr/pers/namer E-mail : Fiammetta.Namer at univ-nancy2.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 Amalia.Todirascu at LORIA.FR Mon Mar 29 15:52:43 2004 From: Amalia.Todirascu at LORIA.FR (Amalia.Todirascu at LORIA.FR) Date: Mon, 29 Mar 2004 13:52:43 -0200 Subject: Last CFP: COLING'04 Workshop on RObust Methods in Analysis of Natural language Data Message-ID: LAST CALL FOR PAPER Submission Deadline: March 31st ROMAND 2004 3rd workshop on RObust Methods in Analysis of Natural language Data A satellite event of COLING 2004 Geneva - August 29th 2004 http://lithwww.epfl.ch/romand2004/ Robustness in Computational Linguistics has been recently recognized as a central issue for the design of interactive applications based on natural language communication. If a failure of the system can be acceptable in batch applications requiring a human intervention, an on-line system should be capable of dealing with unforeseen situations in a more flexible way. When we talk about system failure we do not think at inherent program failures like infinite loops or system exception, we consider, rather, failures related to the processing of the input and its assimilation in the system's knowledge base. A failure of this kind means simply that the system does not "understand" the input. The automated analysis of natural language data has become a central issue in the design of Intelligent Information Systems. Processing unconstrained natural language data is still considered an AI-hard task. However, various analysis techniques have been proposed in order to address specific aspects of natural language. In particular, recent interest has been focused on providing approximate analysis techniques, assuming that when perfect analysis is not possible, partial results may be still very useful. ROMAND 2004 is the third of a series of workshops aimed at bringing together researchers and students that work in fields like artificial intelligence, computational linguistics, human-computer interaction, cognitive science and are interested in robust methods in natural language processing and understanding. The term "natural language" is intended as all the possible modalities of human communication and it is not restricted to written or spoken language. Theoretical aspects of robustness in Natural Language Processing (NLP) and Understanding (NLU) are welcome as well as engineering and industrial experiences. We are also interested in research works that investigate different types of linguistic modules integration, in order to characterise their advantages and disadvantages with respect to different types of applications, and works that propose different types of NLP/NLU systems, ranging from sequential/pipelined architectures to more loosely-coupled multi-level distributed architectures. We invite papers on all topics related to robustness in natural language processing, including, but not limited to: * Natural Language Architectures * Robust Morpho-Syntactic Parsing * Robust Semantics * Robust Discourse Analysis * Robust Computational Pragmatics * Complexity of linguistic analysis * Spell checking and automated spell correction * NLP and Soft Computing * Hybrid methods in computational linguistics * Information Extraction * Multimedia Document Analysis * Spoken Language Understanding * Multimodal Human-Computer Interfaces * Cognitive Linguistics INVITED TALKS Dr. Frank Keller, University of Edinburgh: "Gradient Grammaticality: Applications in Robust Parsing" SUBMISSION PROCEDURE: Authors should submit an anonymous paper (avoiding, as much as possible, hints for the identification of authors) of at most 10 pages (including pictures and references), intended for talks with a duration of minutes plus 10 minutes for discussions. The paper should follow the COLING formatting style available on the main conference web site (http://www.issco.unige.ch/coling2004/), and the authors must also send us a wrapper e-mail message indicating: 1. the AUTHOR'S NAMES, AFFILIATION, ADDRESS, and E-MAIL address of (at least) the contacting author, 2. an ABSTRACT of the submitted paper (less than 500 words), 3. a list of KEYWORDS (no more than 5). The papers should be submitted electronically in PDF (preferred) or postscript format to: mailto:romand at epfl.ch. IMPORTANT DATES: Papers submission: March 31st Acceptance notification: May 7th Final version: June 4th Workshop: August 29th PROGRAM CHAIRS Vincenzo Pallotta (Swiss Federal Institute of Technology - Lausanne and International Computer Science Institute - Berkeley) Amalia Todirascu (University of Troyes and University of Iasi) PROGRAM COMMITTEE Afzal Ballim Alberto Lavelli Alexander Clark Atro Voutilainen Bangalore Srinivas C.J. Rupp Dan Cristea Diego Molla'-Aliod Eric Wherli Jose' Iria Fabio Massimo Zanzotto Fabio Rinaldi Frank Keller Giovanni Coray Guenther Goerz Hatem Ghorbel Jean-Cedric Chappelier Jean-Pierre Chanod Joachim Niehren John Carroll Kay-Uwe Carstensen Manuela Boros Maria Teresa Pazienza Martin Rajman Michael Hess Patrick Ruch Roberto Basili Rodolfo Delmonte Salah Ait-Mokhtar Susan Armstrong Wolfgang Menzel Yuji Matsumoto LOCAL ORGANIZATION Violeta Seretan (University of Geneva) Hatem Ghorbel (Swiss Federal Institute of Technology - Lausanne) CONTACT INFORMATION: All inquiries should be sent to [romand at epfl.ch]. Please note that general organizational details (registration, accommodation, etc.) are taken care of by COLING 2004, not by the workshop organizers. More information are available the workshop's Web page at http://lithwww.epfl.ch/romand2004/ ------------------------------------------------------------------------- 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 Mar 30 09:54:59 2004 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Tue, 30 Mar 2004 11:54:59 +0200 Subject: Conf: TALN 2004 : Atelier QUESTION-REPONSE Message-ID: ********************************************************************** Dans le cadre de la conférence T A L N 2 0 0 4 Atelier QUESTION-REPONSE http://www.lpl.univ-aix.fr/jep-taln04/question-answer.htm Palais de Congrès Fès (Maroc) Le 22 avril 2004 ********************************************************************** Programme 9h - 10h - Conférence invitée Automatic Induction of Text Entailment Patterns for Question Answering Bernardo Magnini, ITC-IRST, Trento, Italie 10h - 11h Deux pistes complémentaires pour améliorer l'appariement Question Réponse Karine Lavenus, Jens Grivolla, Laurent Gillard, Patrice Bellot, LIA, Avignon Filtering Out Bad Answers with Semantic Relations in a Web-Based Question-Answering System Leila Kosseim and Jamileh Yousefi, CLaC lab., Concordia University, Montreal, Canada Ressources pour un Système de Question/Réponse Eric Crestan, Elise Lemaire, Claude de Loupy, Sinequa, Ivry-sur-Seine, LIA, Avignon, MoDyCo, Nanterre 11h - 11h30 - pause 11h30 - 12h30 Using semantic information to improve the performance of a restricted-domain question-answering system Hai Doan-Nguyen and Leila Kosseim, CLaC lab., Concordia University, Montreal, Canada The importance of How-questions in technical domains Rolf Schwitter, Fabio Rinaldi, Simon Clematide, Macquarie University, Sydney, Australie et University of Zurich 12h30 - 14h - pause déjeuner 14h - 15h Génération de requêtes pour les systèmes de Q/R avec un modèle d'apprentissage statistique Nicolas Usunier, Massih Reza Amini, Patrick Gallinari, Brigitte Grau, LIP6, Paris et LIMSI, Orsay L'analyse des questions : intérêts pour la génération des réponses Sara Mendes, Véronique Moriceau, CLUL, Lisbonne et IRIT, Toulouse 15h - 15h20 - pause 15h20 - 16h Présentation de EQUER, la campagne d'évaluation des systèmes de question-réponse sur le français. EQUER fait partie du projet Technolangue EVALDA sous la responsabilité de ELDA Maria Nava, ELDA Discussion -- Groupe LIR - LIMSI BP 133, 91403 Orsay Cedex tel. 01 69 85 80 03, fax 01 69 85 80 88 et Institut d'Informatique d'Entreprise (IIE) 18 all?e Jean Rostand, 91025 Evry Cedex tel. 01 69 36 73 44, fax 01 69 36 73 09 mail : grau at iie.cnam.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 thierry.hamon at LIPN.UNIV-PARIS13.FR Tue Mar 2 11:47:25 2004 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Tue, 2 Mar 2004 12:47:25 +0100 Subject: Conf: RIAO 2004, April 26-28, 2004 Message-ID: Date: Sun, 29 Feb 2004 23:53:46 +0100 From: Ibekwe Message-ID: <40426D7A.7070709 at univ-lyon3.fr> X-url: http://www.riao.org Apologies for multiple postings Please find the program for the the seventh RIAO conference. You know that RIAO 2004 will take place in Avignon "Vaucluse", France from April 26 to April 28. Please send this program as much as you can around you. Thank you in advance. You will find more information on the web site and a French version if you need it : www.riao.org. We will be happy to welcome you in Avignon Sincerely G. Grefenstette, co-chair of the program committee information at riao.org RIAO'2004 Coupling Approaches, Coupling Media and Coupling Languages for Information Retrieval PROGRAM University of Avignon (Vaucluse - France) 26-28 Avril 2004 www.riao.org The seventh RIAO conference is organised by: CENTRE DE HAUTES ETUDES INTERNATIONALES D'INFORMATIQUE DOCUMENTAIRE (C.I.D., France) in collaboration with the LIA (Laboratoire d'Informatique d'Avignon - Universit? d'Avignon) with technical support from l'IRIT (Institut de Recherche en Informatique de Toulouse) in cooperation with the Commissariat ? l'Energie Atomique (CEA) LIST Introduction Current content-based information management involves many different disciplines. Information must be retrieved from video, from sound, and from images and graphs. Question answering involves both syntax and semantics. Information classification and filtering involve machine learning and linguistics. In addition, as information technology spreads throughout the world, a wider variety of languages in increasingly complex combinations must be handled. In response to these evolving needs, RIAO'2004 conference will cover the coupling of techniques from different domains to improve information retrieval. RIAO'2004 will present innovative research and developments from all areas of multi-media and multi-language information retrieval. Combination of techniques from disparate domains, will treat retrieval from either a single medium, or across media (indexing one medium for find information in another), or from coupling unstructured and structured information (e.g. exploiting both text and XML structure), or from across languages. RIAO'2004 presents recent scientific progress in these areas with oral presentations, demonstrations of research prototypes, as well as presenting a selection of innovative products present on the market. RIAO (which stands for Recherche d'Information Assist?e par Ordinateur ) is organized every three years since 1985. Previous RIAO Conferences were held in Grenoble, France (1985), at MIT in Cambridge Massachussetts. USA (1988), in Barcelona, Spain (1991), in New York USA (1994), at Mc Gill, Montreal (1997), and at the Coll?ge de France, Paris (2000) The conference is organized by the Centre de Hautes Etudes Internationales d'Informatique Documentaire (C.I.D.) in conjunction with various partners. This year's conference presents research from 18 different countries, two invited keynote speeches, 13 sessions of oral presentations, a poster session and a session dedicated to cultural applications. The 51 papers presented, 16 posters, and various presentations will give an overview of the state-of-the-art in this rapidly changing domain. Concurrent to the scientific presentations, a wide variety of innovative applications will be presented by an international selection of companies. Each application was chosen by an Applications Committee using the same criteria of quality and originality as the Scientific Committee for the written scientific communications. Programme RIAO 2004 Monday, April 26 08:00 - 9:30 Registration 09:30 - 10:15 Welcome from officials 10:15 - 11:00 Invited speaker 11:00 - 11:15 Coffee break 11:15 - 12:35 Session 1: Indexing Video, Sound and Images The F?schl?r-News-Stories System: Personalised Access to an Archive of TV News Alan Smeaton, Cathal Gurrin, Hyowon Lee, Kieran McDonald, Noel Murphy, Noel O'Connor, Dublin City University Video Summarization Based on User-Defined Constraints and Preferences Vyacheslav Parshin, Liming Chen, Ecole Central de Lyon, Dept. Math?matique-Informatique The TREC VIdeo Retrieval Evaluation (TRECVID): A Case Study and Status Report Alan Smeaton, Dublin City University Wessel Kraaij, TNO TPD Paul Over, NIST CIMWOS: A Multimedia Retrieval System based on Combined Text, Speech and Image Processing Harris Papageorgiou, Prokopis Prokopidis, Lason Demiros, Nikos Hatzigeorgiou, Georges Carayanis, Institute for Language and Speech Processing (ILSP) 12:35 - 13:45 Lunch 13:45 - 15:25 Session 2: Searching across Languages Multilingual Information Retrieval with Asian Languages Jacques Savoy, University of Neuchatel Transitive CLIR Models Wessel Kraaij, TNO Franciska de Jong, University of Twente Interlingual Indexing across Different Languages Kornel Marko, Udo Hahn, Linguistische Informatik Stefan Schulz, Philipp Daumke, Medizinische Informatik Crossing Languages in Text Retrieval via an Interlingua Udo Hahn, Michael Poprat, Linguistische Informatik Stefan Schulz, Joachim Wermter, Kronel Marko, Medizinische Informatik Multilingual document clusters discovery Benoit Mathieu, Christian Fluhr, Romaric Besan?on, CEA - LIST/LIC2M 15:25 - 15:55 Break / Demonstrations 15:55 - 16:55 Session 3: Searching and Ontologies Ontologies as Background Knowledge to Explore Document Collections Aussenac Nathalie, Mothe Josiane, IRIT Learning ? Generalization/Specialization ? Relations between Concepts - Application for Automatically Building Thematic Document Hierarchies Hermine Njike Fotzo, Patrick Gallinari, Lip6 Coupling Information Extraction and Data Mining for Ontology Learning in PARMENIDES Myra Spiliopoulou, University of Magdeburg Fabio Rinaldi, University of Zurich Bill Black, UMIST, Manchester Gian Piero Zarri, CNRS, Paris 16:55 - 17:55 Session 4: Niche Web Systems Combinaison de classifieurs pour le filtrage de documents multi-m?dias ? caract?re choquant ou dangereux Bruno Grilheres, EADS S&DE/PSI Rouen Stephan Brunessaux, EADS S&DE Philippe Leray, PSI Rouen Coupling Niche Browsers and Affect Analysis Gregory Grefenstette, Yan Qu, James G. Shanahan, David A. Evans, Clairvoyance Corporation, Pittsburgh, PA, USA Bilingual PRESRI - Integration of Multiple Research Paper Databases - Hidetsugu Nanba, School of Information Sciences, Hiroshima City University Takeshi Abekawa, Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology Manabu Okumura, Suguru Saito, Precision and Intelligence Laboratory, Tokyo Institute of Technology 17:55 - 18:15 Cultural heritage applications Un mus?e virtuel pour les sp?cialistes Marie-Fran?oise Clergeau, Coll?ge de France Fabritius : base de donn?es multilingue en ligne pour les Mus?es royaux des beaux-arts de Belgique Pierre-Yves Desaive, Mus?es Royaux des Beaux-Arts de Belgique 18:30 Cocktail in the "Salle de la grande audience" of the Popes' Palace Tuesday, April 27 09:00 - 09:45 Invited speaker 09:45 - 11:05 Session 5: Different Methods and Languages for Question Answering ASKMi: A Japanese Question Answering System based on Semantic Role Analysis Tetsuya Sakai, Yoshimi Saito, Yumi Ichimura, Makoto Koyama, Tomoharu Kokubu, Toshihiko Manabe, Toshiba Corporate R&D Center A Pattern Based Approach to Factoid and Definition Question Answering Horacio Saggion, Mark Greenwood, University of Sheffield Question-Answer Matching : Complementary Methods Karine Lavenus, Jens Grivolla, Laurent Gillard, Patrice Bellot, LIA, Universit? d'Avignon, France MOQA - Meaning-Oriented Question-Answering Jim Cowie, New Mexico State University, CRL Sergei Nirenburg, University of Maryland, ILIT Tanya Korelsky, CoGenTex, Inc. Stephen Helmreich, New Mexico State University, CRL Beno?t Lavoie, CoGenTex, Inc. 11:05 - 11:40 Break / Demonstrations 11:40 - 13:00 Session 6: Image Processing Image Understanding using Domain Knowledge Nicolas Zlatoff, Bruno Tellez, Atilla Baskurt, LIRIS Improving CBIR systems by integrating semantic features Djamel Brahmi, Djemel Ziou, Universit? de Sherbrooke (Canada) Automatic generation of natural language description for images. Patrick Hede, Pierre-Alain Mo?llic, Magali Joint, Jo?l Bourgeoys, Hubert Naets, CEA LIST/LIC2M Costume: A New Feature for Video Content Indexing Ga?l Jaffr?, Philippe Joly, IRIT 13:00 - 14:30 Lunch 14:30 - 15:50 Session 7 (parallel session): Cooperative Searching andusers Group Memory Based on the Task Information Jonathan Yu, James Thom, RMIT University Leila Alem, CSIRO BINGO! and DAFFODIL: Personalized Exploration of Digital Libraries and Web Sources Martin Theobald, Max-Planck Institut f?r Informatik Claus-Peter Klas, Universit?t Duisburg The Generalized Web Surfer Ayman Farahat, Francine Chen, Palo Alto Research Center Improving Ontology-Based User Profiles Joana Trajkova, Susan Gauch, University of Kansas 14:30 - 15:50 Poster session (parallel session) OWL-based reasoning with retractable inference Carlo Jelmini, Stephane Marchand-Maillet, Viper Group - University of Geneva Browsing and searching e-encyclopaedias Ruth Wilson, Julie Shortreed, Monica Landoni, University of Strathclyde An Experiment with Ontology Mapping using Concept Similarity Robert Villa, Ruth Wilson, Fabio Crestani, University of Strathclyde Coupling OWL with MPEG-7 and TV-Anytime for Domain-specific Multimedia Information Integration and Retrieval Chrisa Tsinaraki, Panagiotis Polydoros, Nektarios Moumoutzis, Stavros Christodoulakis, Lab. of Distributed Multimedia Information Systems and Applications (MUSIC/TUC) Speaker segments regroupment Liming Chen, Aliaksandr Paradzinets, Ecole Centrale de Lyon Rich Document Representation for Document Clustering Azam Jalali, Department of Computer & Electrical Engineering, University of Tehran, Farhad Oroumchian, University of Wollongong in Dubai Audio Documents Analysis And Indexing: Entropy And Dynamism Criteria Liming Chen, Dept. Math?matiques Informatique, Ecole Centrale de Lyon, France Eugeny Bovbel, Hanna Lukashevich, Department of Radiophysics, Byelorussian Denis Mitrofanov, Department of Radiophysics, Byelorussian State University, Belarus Suivi du Locuteur dans des Discours Multim?dia Halim Sayoud, Siham Ouamour, USTHB Information retrieval on mixed written and spoken documents Benoit Favre, Patrice Bellot, Jean-Fran?ois Bonastre, Laboratoire d'Informatique d'Avignon Mod?lisation de connaissances et fouille d'informations par la cartographie dynamique : application de veille technologique avec Matheo Analyzer Mylene Leitzelman, H Dou, J Kister, Faculte Sciences et Techniques de St-J?r?me Improving the Precision of a Closed-Domain Question-Answering System with Semantic Information Hai Doan-Nguyen, Leila Kosseim, Department of Computer Science, Concordia University Retrieving what's relevant in audio and video: statistics and linguistics in combination Anthony Davis,Phil Rennert, Robert Rubinoff, Tim Sibley, Evelyne Tzoukermann StreamSageToward Tacit Information Retrieval Daniel Memmi, IMAG Grenoble Automating Indexing of Classes and Conferences Jean-Claude Moissinac, Fran?ois Yvon, Slim Ben Hazez, GET/ENST Indexation automatique de documents par combinaison d'analyses statistiques et terminologiques structur?es Lyne Da Sylva, ?cole de biblioth?conomie et des sciences de l'information, Universit? de Montr?al Information Retrieval and Extraction from the Web: the CROSSMARC approach Vangelis Karkaletsis, Constantine Spyropoulos, NCSR "Demokritos", Institute of Informatics & Telecommunications 15:50 - 16:10 Break / demonstrations 16:10 - 17:30 Session 8 (parallel session): User Searching, Studies and Aids Subject knowledge, thesaurus-assisted query expansion and search success Anne Sihvonen, Pertti Vakkari, University of Tampere Fetch: A Personalised Information Retrieval Tool Innes Martin, Joemon Jose, University of Glasgow Interfaces dynamiques de fouille textuelles Javier Couto, Jean-Luc Minel, Laboratoire LaLICC, CNRS-Universit? Paris-Sorbonne Feedback Mechanisms for a Natural Language Interface: An Application of the Critic Paradigm Johannes Leveling, Fern Universit?t in Hagen 16:10 - 17:10 Session 9 (parallel session): New views on Relevance Improving the Relevance-based Superimposition model for IR with automatic keyword extraction Teruhito Kanazawa, KYA group Atsuhiro Takasu, Jun Adachi, National Institute of Informatics Evaluation of Retrieval Systems without Predefined Retrieval Unit Arjen de Vries, CWI Gabriella Kazai, Mounia Lalmas, Queen Mary University London Monitoring user-system performance in interactive retrieval tasks Liudmila Boldareva, University of Twente (UT) Arjen de Vries, National Research Institute for Mathematics and Computer Science (CWI) Djoerd Hiemstra, University of Twente (UT) 17:30 - 18:30 Conference given by Michel Laclotte, Directeur G?n?ral honoraire of the Louvre Museum ? L'?cole d'Avignon, Deux Si?cles de Peinture ? 19:00 Guided tour of the "Palais des Papes" 20:15 Conference Dinner Wednesday, April 28 09:30 - 10:50 Session 10: Mono and Multilingual Term Variation Mining textual data through term variant clustering : the TermWatch system Fidelia Ibekwe-Sanjuan, ERSICOM - Universit? de Lyon 3 Eric Sanjuan, LITA - Universit? de Metz Knowledge Acquisition from Collections of News Articles to Cross-Language Information Retrieval Fatiha Sadat, National Institute of Informatics (NII) Chinese character expansion for retrieving Japanese paraphrases Takenobu Tokunaga, Yoshiki Tezuka, Hozumi Tanaka, Tokyo Institute of Technology Cross-Language Image Retrieval via Spoken Query Wen-Cheng Lin, Ming-Shun Lin, Hsin-Hsi Chen, Department of Computer Science and Information Engineering, National Taiwan University 10:50 - 11:15 Break / demonstrations 11:15 - 12:35 Session 11: Conceptual, Structural Retrieval, XML Source Code Retrieval using Conceptual Similarity Gilad Mishne, Maarten de Rijke, ILLC, University of Amsterdam Multimodal Indexation of Contrastive Structures in Geographical Documents Antoine Widl?cher, Eric Faurot, Fr?d?rik Bilhaut, GREYC - Universit? Ca?n Integrating XLink and XPath to Retrieve Structured Multimedia Documents in Digital Libraries Zhigang Kong, Mounia Lalmas, Department of Computer Science, Queen Mary, University of London Using XML to Query XML - From Theory to Practice Andrei Broder, IBM T.J. Watson Research Center Yoelle Maarek, Yosi Mass, Matan Mandelbrod, IBM Haifa Research Lab 12:35 - 14:00 Lunch 14:00 - 15:40 Session 12: Topic Discovery, Segmentation Summarizing Texts at Various Levels of Detail Marie-Francine Moens, Roxana Angheluta , Rik De Busser, Patrick Jeuniaux, Katholieke Universiteit Leuven Selective Combination of Evidence for Topic Distillation using Document and Aggregate-level Information Vassilis Plachouras, Iadh Ounis, University of Glasgow Fidel Cacheda, University of A Coruna Comparing algorithms for French linear segmentation Laurianne Sitbon, Patrice Bellot, LIA, Universit? d'Avignon, France Tagging Well-known Arabic Names to Support Question-Answering Systems Saleem Abuleil, Chicago State University Unsupervised Learning with Term Clustering for Thematic Segmentation of Texts Marc Caillet, Jean-Fran?ois Pessiot, Massih-Reza Amini, Patrick Gallinari, Laboratoire d'Informatique de Paris 6 15:40 - 15:50 Break 15:50 - 17:00 Session 13: Improving Retrieval Combining Positive and Negative Query Feedback in Passage Retrieval Dkaki Taoufiq, Mothe Josiane, IRIT Latent Semantic Indexing with a Variable Number of Orthogonal Factors Georges Dupret Word Pairs in Language Modeling for Information Retrieval Carmen Alvarez, Philippe Langlais, Jian-Yun Nie, Universit? de Montr?al A Query-based Pre-retrieval Model Selection Approach to Information Retrieval Ben He, Iadh Ounis, Department of Computing Science, University of Glasgow 17:00 - 17:30 Closing session Innovative Applications Innovative applications and products related to the conference topics are sought for demonstrations during the three days of the Conference. They will be selected by the international Application committee, on the basis of their innovation and future or present marketability. Selected applications will be given free demonstration spaces. The selection of the innovative applications and products is not finished. The list of accepted ones will be soon available on the RIAO web site Applications and products will be chosen among the following topics: * Multimedia indexing and retrieval systems (text, sound, speech, images, video) * Cross-lingual indexing and retrieval systems * Peer-to-peer text search engines * Cooperative Information Retrieval (grids) * Automatic XML structuring of documents * Automatic metadata generation for text, sound, and images, automatic annotators * Automated ontology construction and annotators * Topic detection and event detection in streaming documents, technology watch, strategy watch * Intelligent message filtering * Intelligent text agents * Parent control and anti-spam control by content filtering * E-learning - response interpretation * Document summarisation -- mono or multilingual, mono or multidocument, profile driven * Topic maps * Domain-specific application of information retrieval and multimedia retrieval: medicine, e-commerce, computer-assisted teaching, video production, etc Demonstrations will be organized all along the conference and short oral presentations will be held in parallel sessions, Monday afternoon (13:45 - 15:25 and 16:55 - 17:55) Committees Program Committee Co-Chairs Christian Fluhr CEA, France Europe, Africa Gregory Grefenstette Clairvoyance Asia, Oceania Bruce Croft Univ. of Mass, Amherst, USA Americas Bruno Bachimont Tech. Univ. of Compi?gne Catherine Berrut IMAG, France Georges Carayanis ILSP, Greece Francine Chen PARC, USA Claude Chrisment IRIT, Toulouse, France Roger Dannenberg CMU, USA Franciska de Jong Univ. Twente, Netherlands Claude de Loupy Sinequa, France Renato De Mori Univ. Avignon, France Marc El-B?ze Univ. Avignon, France Pascale Fung Scienc. Tech. Univ., Hong Kong Sadaoki Furui Tokyo Inst. Tech., Japan Jean-Luc Gauvain LIMSI, France Edouard Geoffrois DGA - CTA/CIP, France Julio Gonzalo UNED, Spain Donna Harman NIST, USA David Hawking CSIRO, Australia Ulrich Heid Univ. Stuttgart, Germany Eduard Hovy ISI, Univ. S. California, USA Christian Jacquemin LIMSI, France Boris Katz MIT, USA Elisabeth Liddy Univ. Syracuse, USA Simone Marinai Univ. Florence, Italy Jos? Martinez Univ. Nantes, France Christof Monz Univ. Amsterdam, Netherlands Frank Nack CWI, Netherlands Chahab Nastar LTU, France Jian-Yun Nie Univ. Montr?al, Canada Douglas Oard Univ. Maryland, USA J?rg Ontrup Univ. Bielefeld, Germany Gabriella Pasi Univ. Milano, Italy Marie Theresa Pazienza Univ. Roma, Italy Carol Peters CNR, Italy Euripides Petrakis Tech. Univ. of Crete, Greece Marc Pic Advestigo, France Jean-Marie Pierrel INALF, France Jean-Marie Pinon INSA Lyon, France Yan Qu Clairvoyance, USA Steve Renals Univ. Sheffield, Great Britain Tetsuya Sakai Toshiba, Japan Fr?d?rique Segond Xerox, France Bernadette Sharp Staffordshire, Great Britain Alan Smeaton Univ. Dublin, Ireland Tokunaga Takenobu Tokyo Inst. Tech., Japan Simone Teufel Univ. Cambridge, Great Britain Evelyne Tzoukermann ACM, USA Alex van Ballegooij CWI, Netherlands Keith Van Rijsbergen Univ. Glasgow, Great Britain James Z. Wang PennState Univ., USA Ross Wilkinson CSIRO, Australia Zhiping Zheng Univ. Saarland, Germany Applications Committee Chair Chantal Soul?-Dupuy Universit? de Toulouse, France Michel Benoit St? Itek, France Robert Bentz Xerox Global Services, France Marie-Fran?oise Clergeau Coll?ge de France Daniel Confland Jouve, France Max Copperman Kanisa, USA Michel Dureigne EADS, France Bernard Dousset Irit, Univ. Paul Sabatier, France P?r? Escorsa Univ. Polytechnic de Catalunya, Spain Muriel Foulonneau Relais Culture Europe, France Christine Jacquet-Pfau Coll?ge de France Dominique Ladiray Insee-Ensac Statistics, Canada Ornella Mich Inst. Trentino di Cultura, Italy Norbert Paquel Canope, France Organisation and Coordination Committee Chair Agn?s Beriot D?l?gu?e G?n?rale du C.I.D., France Henriette Allignon C.I.D., France Peter Brodnitz Ogilvy & Mather, Japan Jean Louis d'Arc F?d?ration France-Poland, France Jean Perri?re Administrator, Secretary General, C.I.D., France Sharyn Rosart CASIS, USA Anne Tabutiaux Recherche et Diffusion, France Local Organisation Committee Aur?lia Barri?re Univ. Avignon, France St?phane Igounet Univ. Avignon, France (Final list forthcoming) Technical Committee Chair Luc Boulianne C.I.D., Canada Jonathan Albert C.I.D., Canada Max Chevalier Univ. Toulouse, France Jean-Jacques Guilbart Coll?ge de France, France C?cile Laffaire Univ. Toulouse, France Registration Registration fees: * 370 euros for early registration received until April 1, 2004 * 430 euros registration after April 1, 2004 * 320 euros early registration for CID members until April 1, 2004 * 430 euros registration for CID members after April 1, 2004 Registration includes admission to all conference sessions, to prototype and product demonstrations, to coffee breaks, and to the Tuesday night conference dinner. It is possible to reserve extra places at this dinner for 25 euros per person. Student fees: * 170 euros for early registration received until April 1, 2004 * 200 euros registration after April 1, 2004 Student registration includes admission to all conference sessions, to prototype and product demonstrations, to coffee breaks, but not to the Tuesday night conference dinner. Students can reserve a place at this dinner for 25 euros per person. Registration instructions: Please register using the secured payment facilities found on our web site http://www.riao.org/. It is also possible to pay by bank transfer to the following account: Name : CID Bank : Soci?t? G?n?rale Branch : Agence Montmartre, 89 rue de Clichy, 75009 Paris, France Account Number : 000 50 06 5481 Rib 06 Bank Number : 30003 Branch Number : 03120 IBAN : FR76 30003 03120 000500065481 06 BIC : SOGEFRPP Payment by check in euros will also be accepted. In this case send your check made out the "C.I.D." along with registration information (as found on the web site) to CID Congr?s RIAO'2004 36 bis rue Ballu 75009 Paris France Note: Registration can be canceled (with a 90% reimbursement of registration fees) until April 5, 2004. After this date no reimbursement will be possible. Final Registration: It will also be possible to register and pay registration fees on Sunday evening April 25 at the Hotel DANIELI 17 rue de la R?publique 84000 Avignon between 6 p.m. and 8 p.m. and on-site on Monday April 26 from 8 a.m. It is nonetheless strongly advised to pre-register in order to avoid long lines the first morning, and to take advantage of the reduced early registration fees before April 1, 2004. Each participant must check-in on-site before the conference at the University of Avignon, to receive their badge, the printed proceedings of the conference and the final program. Conference Dinner: The conference dinner will be held at the: "Grenier ? Sel" 2, rue du Rempart Saint-Lazare, 84000 Avignon (33) (0) 4 90 27 09 09 http://www.grenieraselavignon.com A map will be distributed at the conferemce. Language: The working language of the conference will be English. In accordance with the French law, it will be possible, nonetheless, to present one's communication in French. Tutorial : Google scientists Vibu Mittal, Shumeet Baluja, and Mehran Sahami plan a tutorial on Web Information Retrieval for Sunday before the conference. This tutorial will be held if a sufficient number of people enroll. Details can be found on the RIAO web site - http://www.riao.org Conference Address: University of Avignon 74, rue Pasteur Avignon H?tels Rooms have been reserved in a number of local hotels until April 1st, 2004. We recommend that you reserve a room as early as possible. Avignon is very active at the time of the conference. A hotel list is available on the RIAO web site. Transport If you are arriving in Paris at the Paris-Roisy Charles de Gaulle airport, you can take a direct high-speed train to Avignon. Check times online at http://www.sncf.com/indexe.htm . A shuttle leaves from the Avignon-TGV station to downtown Avignon. If you are arriving in Paris at the Orly airport, there are direct flights to Avignon (a?roport national) except on Sundays. Marseille-Marignane is an international airport situated 70 kms from Avignon. You might find a connection arriving there. If you are planning to come through Marseilles, please notify the conference organizers at informations at le-cid.org telling us when you are arriving and we might be able to organize a shuttle to Avignon. Information Centre de Hautes Etudes Internationales d'Informatique Documentaire (C.I.D.) 36 bis rue Ballu 75009 Paris France Tel: (33 / 0) 1 42 85 04 75 Fax: (33 / 0) 1 48 78 49 61 Email: information at le-cid.org Web: http://www.riao.org Revision: February 26, 2004 ------------------------------------------------------------------------- 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 Fri Mar 5 16:57:03 2004 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Fri, 5 Mar 2004 17:57:03 +0100 Subject: Appel: Enhancing and using electronic dictionaries, Coling workshop Message-ID: Date: Thu, 4 Mar 2004 17:50:43 +0900 From: Michael Zock Message-Id: X-url: http://www.limsi.fr/Individu/zock/coling2004workshop.html X-url: http://www.issco.unige.ch/coling2004/ X-url: http://www.issco.unige.ch/coling2004/coling2004downloads.html Enhancing and using electronic dictionaries Michael Zock (Limsi, CNRS) & Patrick St. Dizier (Irit, CNRS) Introduction A dictionary is a vital component of any natural language processing system. Its modern, digital form has considerable potential, especially if it is extended and built in a way compatible with the needs and habits of the average language user. There are many ways to make an electronic dictionary useful for people in their daily tasks of processing language. One could assist 1. reading and writing: adding a transliterator and a morphological generator/parser to a dictionary would put the needed information at the distance of a mouse click. Imagine someone trying to look up the meaning (or translation) of a word in a script he can?t read. 2. language learning: combining dictionaries with a parametrizable flashcard system and a goal-driven exercice generator could help the memorization and automation of words and basic syntactic patterns. In such a system choosing a goal would trigger syntactic templates, filling the latter with words would yield (simple) sentences. 3. lexical access (navigation): structuring the dictionary in a similar way as the human mind, i.e. building an associative network akin to WordNet, but with many more links in particular at the syntagmatic axis, could assist the writer not only in finding new ideas (brainstorming), but also the word he is looking for. Within this framework, word access amounts to entering and navigating in a huge, associative network. To build such a tool one could extract associations from an encyclopedia, label and add them as links to a resource like WordNet. As one can see, there are numerous ways to enhance dictionaries. While the new hardware offers many, sometimes surprising opportunities for novel uses, seizing them requires some rethinking. This is the goal of this one-day workshop. In particular, we?d like to discuss interesting extensions and enhancements of electronic dictionaries. For example, one could consider merging different, thesaurus-like dictionaries and see what kind of conceptual and navigational aids might be added to support the language user: what are his needs, what information is he looking for? Actually, a focus shift might be necessary to move from the data (content and size of the dictionary) to their organisation and access. As, what is a huge dictionary good for, if one cannot find the word one is looking for? Target audience The aim of this workshop is to bring together leading researchers involved in the building of electronic dictionaries to discuss modifications of existing resources in line with the users? needs (i.e. how to capitalize on the advantages of the digital form). Given the breadth of the questions, we welcome reports on work from many perspectives, including, but not limited, to linguistics, computer science, psycholinguistics, language learning, and ergonomics. We request that each contribution addresses computational aspects. Topics We would like to invite papers addressing any of the following issues: type of information to be stored in the dictionary representation and structuring (indexing) of the data; management, visualization and useability of the data; access (aids for navigation, interface, strategies); acquisition of lexical data (corpus); possibilities for editing entries (annotation, updating); integration (combination of the dictionary with other ressources, writer?s workbench); uses of dictionaries by people (learning/teaching; writing) and by machines (NLP). Submission instructions Papers should be original, hence report on previously unpublished work. Papers simultaneously submitted to other conferences should reflect this fact on the title page. As the review process will not be blind, papers should contain the names and affiliations of authors. Submissions must be electronic only, and should consist of full papers of max. 8 pages (inclusive of references, tables, figures and equations). Project notes and position papers should not exceed 4 pages. Authors should follow the COLING 2004 formating guidelines, available at: http://www.issco.unige.ch/coling2004/coling2004downloads.html. All submissions should be made by email to the following address zock at limsi.fr. They should consist of a single PDF file. Before submitting your document, please verify that all non-standard fonts are correctly embedded in your PDF file (you can do this by disabling the "Use Local Font" option when viewing your document with Adobe's Reader). Formating requirements for the final version of the papers will be posted as soon as they become available. Important dates * Deadline for workshop paper submissions: 1st May 2004 * Notification of workshop paper acceptance: 1st June 2004 * Deadline for camera-ready workshop papers: 15th June 2004 * Workshop Date: 29th August 2004 Organising Committee: * Michael Zock (Limsi-CNRS, Orsay, France) chair * Patrick Saint Dizier (IRIT-CNRS, Toulouse, France) Program Committee: * Antonietta Alonge (University of Perugia, Italy) * Christian Boitet (GETA, Grenoble, France) * Nicoletta Calzolari (ILC-CNR, Pisa, Italy) * Christiane Fellbaum (University of Princeton, USA) * Graeme Hirst (University of Toronto, Canada) * Mathieu Mangeot-Nagata (NII, Tokyo) * Rada Mihalcea (University of North Texas, USA) * Alain Polgu?re (OLST, University of Montreal, Canada) * James Pustejovsky (University of Brandeis, USA) * Gilles S?rasset (GETA, Grenoble, France) * Patrick Saint Dizier (IRIT-CNRS, Toulouse, France) * Takenobu Tokunaga (Tokyo Institute of Technology, Tokyo, Japan) * Dan Tufis (RACAI, Bucharest, Roumania) * Jean V?ronis (University of Aix en Provence, France) * Piek Vossen (Irion Technologies, Delft, The Netherlands) * Leo Wanner (University of Stuttgart, Germany) * Michael Zock (Limsi-CNRS, France) Contact For any queries please contact Michael Zock: zock at limsi.fr ........................................................ Michael ZOCK c/o Professor Tokunaga Department of Computer Science Graduate School of Information Science and Engineering Tokyo Institute of Technology Oookayama 2-12-1, Meguro Ku TOKYO 152-8552/ Japan url: http://www.limsi.fr/Individu/zock/ ------------------------------------------------------------------------- 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 Fri Mar 5 16:57:26 2004 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Fri, 5 Mar 2004 17:57:26 +0100 Subject: Appel: 7th INTEX/NooJ Workshop (2nd CFP) Message-ID: Date: Fri, 05 Mar 2004 16:17:47 +0100 From: Maurel Denis Message-Id: <5.0.0.25.0.20040305161559.00a8ae00 at rabelais.univ-tours.fr> X-url: http://tln.li.univ-tours.fr/JIntex2004/ 7th INTEX/NooJ Workshop Tours, June 7-9 2004 Call for papers - Deadline: March 31, 2004 ORGANIZERS * Laboratoire d'Informatique de l'Universit? de Tours (E.A. 2101) * Langues et Repr?sentation, Equipe de recherche en linguistique, Universit? de Tours * LAboratoire de SEmioLinguistique, Didactique et Informatique (E.A. 2281) CALL We invite the submission of papers for the forthcoming seventh INTEX/NooJ workshop, to be held in Tours, June 7-9 2004. INTEX is a linguistic development environment that includes large-coverage dictionaries and grammars, and parses texts of several million words in real time. INTEX includes tools to create and maintain large-coverage lexical resources, as well as morphological and syntactic grammars. Dictionaries and grammars are applied to texts in order to locate morphological, lexical and syntactic patterns, remove ambiguities, and tag simple and compound words. INTEX can build lemmatized concordances of large texts from Finite-State or Context-Free grammars, and can accordingly perform transformation operations on texts in cascade, in order to annotate the text, or to generate paraphrases; these features, when applied in cascade, give INTEX the power of a Turing Machine. INTEX is used as a linguistic platform, an information retrieval system, to teach second languages, as a terminological extractor, as well as to teach computational linguistics to students. NooJ, which uses a new technology, a new linguistic engine and a new interface, is meant to replace INTEX. NooJ's architecture was presented in the 5th INTEX Workshop (Marseille, June 2002) and its first alpha version was demoed at the 6th INTEX Workshop (Sofia, May 27-29 2003). As in the previous workshops (1996, 1999, 2000, 2001, 2002 and 2003), this meeting will be the opportunity for INTEX and NooJ users, as well as other researchers interested in NLP, to meet and to exchange their experience of development, research or teaching. It will also be the occasion to present the recent developments of NooJ. Please, send before March 31st 2004 a one-page abstract to Denis Maurel by email. The abstract, in French or English, should contain the title of the article, name, author affiliations, surface mail and electronic address of each author. All papers will be reviewed by the program committee. Authors will be notified whether their papers are accepted or rejected by April 15th 2004. The timeslot is 30 minutes for presentations (including 5 minutes for discussions). After the conference, authors will be invited to send a definitive version of their papers for publishing. We are planning to combine a subset of the proceedings of the 6th and the 7th INTEX Workshops in a published volume. PROGRAM COMMITTEE * Xavier Blanco (Universidad Autonoma de Barcelona, Spain) * Gis?le Chevalier (Universit? de Moncton, Canada) * Ibekwe-SanJuan Fidelia (Universit? de Lyon 3, France) * Nathalie Friburger (LI, Universit? de Tours, France) * Svetla Koeva (BACL, IBL - BAS, Sofia, Bulgaria) * Stoyan Mihov (BACL, CLPP - BAS, Sofia, Bulgaria) * Denis Maurel (LI, Universit? de Tours, France) * Paul Sabatier (LIM, CNRS, Marseille, France) * Agata Savary (LI, Universit? de Tours, France) * Henrik Selsoe Sorensen (Copenhagen Business School, Danemark) * Max Silberztein (LASELDI, Universit? de Franche-Comt?, France) * Tamas Varadi (Hungarian Academy of Sciences, Hungary) * Dusko Vitas (MATF, University of Belgrade, Serbia) DEADLINES Submission due date: March 31, 2004 Notification date: April 15, 2004 Registration: May 1, 2004 Camera ready date: June 30, 2004 NooJ TUTORIALS by Max Silberztein * Initiation Tutorial, 20 persons maximum * Teaching Linguistics with NooJ, 20 persons maximum REGISTRATION FEE The registration fee for the workshop is 30 euros for researchers, 15 euros for students and 40 euros for other categories. The conference will begin on Monday morning and last till Wednesday evening. During the Conference there will be a reception on Monday evening and an optional excursion on Tuesday afternoon. CONTACT denis.maurel at univ-tours.f max.silberztein at univ-fcomte.fr Web site: http://tln.li.univ-tours.fr/JIntex2004/ ------------------------------------------------------------------------- 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 Fri Mar 5 16:58:39 2004 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Fri, 5 Mar 2004 17:58:39 +0100 Subject: Appel: Bulag, Divergence in translation between Asian languages and French Message-ID: Date: Fri, 5 Mar 2004 09:00:10 +0800 From: "CHAO Hui-Lan\(?????????\)" Message-ID: <010401c4024d$3681a560$1fa57f8c at chen> X-url: http://tesniere.univ-fcomte.fr/ressources/blgmoden.rtf Call for papers BULAG Special number ?Divergence in translation between Asian languages and French? Context One single and same idea can be verbalized in various ways depending on the languages employed; texts in different languages which are the result of translation reveal divergences at all linguistic levels. Such divergences are due to what? The languages origin is evidently not the only reason, every language possessing its own lexicon, syntax and pragmatics. Moreover, a given text, that is generated (and interpreted as well) in a communicative situation with our cognitive luggage and socio-cultural background, constitutes a body which is complex and whose components are connected synergically and this too, in a way that is appropriate for each language. In this context, the aim of this number of the BULAG is to shed light on questions such as: ?what is the nature of the divergence observed in translated texts?, ?what are the sources of this divergence?, and ?what are the processes which enable eliminating diversity between languages in order to obtain semantic equivalence? Topics The following are privileged topics (which does not exclude others that are related to the subject): Linguistics/translation - Translation divergence under its multiple linguistic facets - Resolution of translation divergence for semantic equivalence Applied linguistics - Tools used for studies on translation divergence - Machine translation and Computer Aided Translation focusing on partial or total restructuring of translation divergences Important dates Submission deadline: June 20, 2004 Author notification: July 30, 2004 Final version (ready for reproduction): October 1, 2004 Submission guidelines The paper is to be written in English or French and sent by preference using electronic mail to the following addresses: huilan at mail.wtuc.edu.tw kyoko.kuroda at nifty.ne.jp In case of the impossibility of sending the paper by electronic mail, a submission sent by post will be accepted. A diskette and a paper copy of the contribution are to be sent to the following address: Hui-Lan CHAO French Department Wenzao Ursuline College of Languages 900, Mintsu 1st Road, 807 Kaohsiung, Taiwan Information concerning the paper's format: RTF format is to be employed. The paper should be a document of 5000 words maximum. An RTF format model for the paper can be downloaded from the following address: http://tesniere.univ-fcomte.fr/ressources/blgmoden.rtf Coordinators Hui-Lan CHAO and Kyoko KURODA Contact huilan at mail.wtuc.edu.tw kyoko.kuroda at nifty.ne.jp ------------------------------------------------------------------------- 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 Fri Mar 5 16:57:57 2004 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Fri, 5 Mar 2004 17:57:57 +0100 Subject: Appel: FOIS-2004 Message-ID: Date: Fri, 5 Mar 2004 13:14:56 +0100 From: "Jos Lehmann" Message-ID: <024001c402ab$809f4040$f0419296 at ip.rm.cnr.it> X-url: http://www.fois.org APOLOGIES FOR MULTIPLE COPIES ==== Call for Papers FOIS-2004 International Conference on Formal Ontology in Information Systems http://www.fois.org November 4-6, 2004, Torino (Italy) == Just as ontology developed over the centuries as part of philosophy, so in recent years ontology has become intertwined with the development of the information sciences. Researchers in such areas as artificial intelligence, formal and computational linguistics, biomedical informatics, conceptual modeling, knowledge engineering and information retrieval have come to realize that a solid foundation for their research calls for serious work in ontology, understood as a general theory of the types of entities and relations that make up their respective domains of inquiry. In all these areas, attention has started to focus on the content of information rather than on just the formats and languages in terms of which information is represented. The clearest example of this development is provided by the many initiatives growing up around the project of the Semantic Web. And as the need for integrating research in these different fields arises, so does the realization that strong principles for building well-founded ontologies might provide significant advantages over ad hoc, case-based solutions. The tools of Formal Ontology address precisely these needs, but a real effort is required in order to apply such philosophical tools to the domain of Information Systems. Reciprocally, research in the information science raises specific ontological questions which call for further philosophical investigations. The purpose of FOIS is to provide a forum for genuine interdisciplinary exchange in the spirit of a unified ontological analysis effort. Although the primary focus of the conference is on theoretical issues, methodological proposals as well as papers dealing with concrete applications from a well-founded theoretical perspective are welcome. == Invited Speakers Peter G?rdenfors, Lund University Cognitive Science, Sweden Amie Thomasson, Department of Philosophy, University of Miami, USA == Deadlines and Further Information Abstracts due May 3, 2004 Final submissions May 7, 2004 Acceptance Notification: June 25, 2004 Submission of camera-ready paper: July 30, 2004 Proceedings will be published by IOS Press and available at the conference. Submission is a two-step procedure: first abstracts, then full papers. Submitted papers must not exceed 5000 words (including bibliography). Abstracts should be less than 300 words. Electronic submission via the website is strongly preferred; if unavailable, submission via email or postal mail is possible. For details see: http://www.fois.org == Conference Chair Nicola Guarino (ISTC-CNR, Trento, Italy) nicola.guarino at loa-cnr.it == Program Chairs Achille Varzi (Columbia University, New York, USA) achille.varzi at columbia.edu Laure Vieu (IRIT-CNRS, Toulouse, France) laure.vieu at irit.fr == Local Chairs Maurizio Ferraris (University of Torino, Italy) ferraris at cisi.unito.it Leonardo Lesmo (University of Torino, Italy) lesmo at di.unito.it == Publicity Chair Jos Lehmann (ISTC-CNR, Rome, Italy) joslehmann at www.ip.rm.cnr.it == Topics We seek high-quality papers on a wide range of topics. While authors may focus on fairly narrow and specific issues, all papers should emphasize the relevance of the work described to formal ontology and to information systems. Papers that completely ignore one or the other of these aspects will be considered as lying outside the scope of the meeting. Topic areas of particular interest to the conference are: Foundational Issues . Kinds of entity: particulars vs. universals, continuants vs. occurrents, abstracta vs. concreta, dependent vs.independent, natural vs. artificial . Formal relations: parthood, identity, connection, dependence, constitution, subsumption, instantiation . Vagueness and granularity . Identity and change . Formal comparison among ontologies . Ontology of physical reality (matter, space, time, motion, ...) . Ontology of biological reality (genes, proteins, cells, organisms, ...) . Ontology of mental reality and agency (beliefs, intentions and other mental attitudes; emotions, ...) . Ontology of social reality (institutions, organizations, norms, social relationships, artistic expressions, ...) . Ontology of the information society (information, communication, meaning negotiation, ...) . Ontology and Natural Language Semantics, Ontology and Cognition Methodologies and Applications . Top-level vs. application ontologies . Ontology integration and alignment; role of reference ontologies . Ontology-driven information systems design . Requirements engineering . Knowledge engineering . Knowledge management and organization . Knowledge representation; Qualitative modeling . Computational lexica; Terminology . Information retrieval; Question-answering . Semantic web; Web services; Grid computing . Domain-specific ontologies, especially for: Linguistics, Geography, Law, Library science, Biomedical science, Ebusiness, Enterprise integration, ... == Programme Committee Bill Andersen, OntologyWorks, USA Nicholas Asher, Dept of Philosophy, University of Texas at Austin, USA Nathalie Aussenac-Gilles, Research Institute for Computer Science, CNRS, Toulouse, France John Bateman, Dept of Applied English Linguistics, University of Bremen, Germany Brandon Bennett, Division of Artificial Intelligence, University of Leeds, UK Andrea Bottani, Dept of Philosophy, University of Bergamo, Italy Joost Breuker, Dept of Computer Science & Law, University of Amsterdam, The Netherlands Roberto Casati, Jean Nicod Institute, CNRS, Paris, France Werner Ceusters, Language & Computing, Belgium Tony Cohn, Division of Artificial Intelligence, University of Leeds, UK Robert Colomb, School of Computer Science and Electrical Engineering, University of Queensland, Australia Ernest Davis, Dept of Computer Science, New York University, USA Martin D?rr, Institute of Computer Science, FORTH, Heraklion, Greece Carola Eschenbach, Dept for Informatics, University of Hamburg, Germany J?r?me Euzenat, INRIA Rh?ne-Alpes, Grenoble, France Christiane Fellbaum, Cognitive Science Laboratory, Princeton University, USA & Berlin Brandenburg Academy of Sciences and Humanities, Berlin, Germany Maurizio Ferraris, Dept of Philosophy, University of Torino, Italy Antony Galton, School of Engineering and Computer Science, University of Exeter, UK Aldo Gangemi, Institute of Cognitive Sciences and Technologies, CNR, Rome, Italy Peter G?rdenfors, Lund University Cognitive Science, Sweden Pierdaniele Giaretta, Dept of Philosophy, University of Padova, Italy Michael Gruninger, Institute for Systems Research, University of Maryland College Park, USA & National Institute for Standards and Technology, USA Nicola Guarino, Institute of Cognitive Sciences and Technologies, CNR, Trento, Italy Patrick J. Hayes, Institute for Human and Machine Cognition, University of West Florida, USA Heinrich Herre, Institute of Informatics, University of Leipzig , Germany Jacques Jayez, ENS-Humanities, Lyon, France Ingvar Johansson, Institute for Formal Ontology and Medical Information Science, University of Leipzig, Germany Hannu Kangassalo, Dept of Computer and Information Sciences, University of Tampere, Finland Fritz Lehmann, USA Leonardo Lesmo, Dept of Computer Science, University of Torino, Italy Bernardo Magnini, Centre for Scientific and Technological Research, ITC, Trento, Italy David Mark, Dept of Geography, State University of New York, Buffalo, USA William E. McCarthy, Department of Accounting, Michigan State University, USA Robert Meersman, Dept of Computer Science, Free University of Brussels, Belgium Chris Menzel, Dept of Philosophy, Texas A&M University, USA Friederike Moltmann, Dept of Philosophy, Stirling University, UK Philippe Muller, Research Institute for Computer Science, University of Toulouse III, France John Mylopoulos, Dept of Computer Science, University of Toronto, Canada Leo Obrst, MITRE, USA Massimo Poesio, Dept of Computer Science, University of Essex, UK Ian Pratt-Hartmann, Dept of Computer Science, University of Manchester, UK James Pustejovsky, Dept of Computer Science, Brandeis University, USA Steffen Schulze-Kremer, German Resource Center for Genome Research, Berlin, Germany Peter Simons, School of Philosophy, University of Leeds, UK Barry Smith, Dept of Philosophy, State University of New York, Buffalo, USA & Institute for Formal Ontology and Medical Information Science, University of Leipzig, Germany John Sowa, USA Veda Storey, Dept of Computer Information Systems, Georgia State University, USA Mike Uschold, The Boeing Company, USA Achille Varzi, Dept of Philosophy, Columbia University, USA Laure Vieu, Research Institute for Computer Science, CNRS, Toulouse, France Yair Wand, Management Information Systems Division, University of British Columbia, Vancouver, Canada Chris Welty, IBM Watson Research Center, USA Roel Wieringa, Computer Science Department, University of Twente, The Netherlands ==== ------------------------------------------------------------------------- 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 Fri Mar 5 16:59:04 2004 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Fri, 5 Mar 2004 17:59:04 +0100 Subject: Appel: Workshop on Robust Methods in Analysis of Natural Language Data, COLING'2004 Message-ID: Date: Thu, 4 Mar 2004 18:30:46 -0100 (MET) From: Message-ID: <38790.193.49.161.187.1078421446.squirrel at www.loria.fr> X-url: http://lithwww.epfl.ch/romand2004/ X-url: http://www.issco.unige.ch/coling2004/), X-url: http://lithwww.epfl.ch/romand2004/ Call For Papers [Submission Deadline: March, 31st 2004] ROMAND 2004 3rd? workshop on RObust Methods in Analysis of Natural language Data A satellite event of COLING 2004 Geneva - August 29th 2004 http://lithwww.epfl.ch/romand2004/ Robustness in Computational Linguistics has been recently recognized as a central issue for the design of interactive applications based on natural language communication. If a failure of the system can be acceptable in batch applications requiring a human intervention, an on-line system should be capable of dealing with unforeseen situations in a more flexible way. When we talk about system failure we do not think at inherent program failures like infinite loops or system exception, we consider, rather, failures related to the processing of the input and its assimilation in the system's knowledge base. A failure of this kind means simply that the system does not "understand" the input. The automated analysis of natural language data has become a central issue in the design of Intelligent Information Systems. Processing unconstrained natural language data is still considered an AI-hard task. However, various analysis techniques have been proposed in order to address specific aspects of natural language. In particular, recent interest has been focused on providing approximate analysis techniques, assuming that when perfect analysis is not possible, partial results may be still very useful. ROMAND 2004 is the third of a series of workshops aimed at bringing together researchers and students that work in fields like artificial intelligence, computational linguistics, human-computer interaction, cognitive science and are interested in robust methods in natural language processing and understanding. The term "natural language" is intended as all the possible modalities of human communication and it is not restricted to written or spoken language. Theoretical aspects of robustness in Natural Language Processing (NLP) and Understanding (NLU) are welcome as well as engineering and industrial experiences. We are also interested in research works that investigate different types of linguistic modules integration, in order to characterise their advantages and disadvantages with respect to different types of applications, and works that propose different types of NLP/NLU systems, ranging from sequential/pipelined architectures to more loosely-coupled multi-level distributed architectures. We invite papers on all topics related to robustness in natural language processing, including, but not limited to: Natural Language Architectures Robust Morpho-Syntactic Parsing Robust Semantics Robust Discourse Analysis Robust Computational Pragmatics Complexity of linguistic analysis Spell checking and automated spell correction NLP and Soft Computing Hybrid methods in computational linguistics Information Extraction Multimedia Document Analysis Spoken Language Understanding Multimodal Human-Computer Interfaces Cognitive Linguistics INVITED TALKS Dr. Frank Keller ? University of Edinburgh: "Gradient Grammaticality: Applications in Robust Parsing" SUBMISSION PROCEDURE: Authors should submit an anonymous paper (avoiding, as much as possible, hints for the identification of authors) of at most 10 pages (including pictures and references), intended for talks with a duration of 20 minutes plus 10 minutes for discussions. The paper should follow the COLING formatting style available on the main conference web site (http://www.issco.unige.ch/coling2004/), and the authors must also send us a wrapper e-mail message indicating: the AUTHOR'S NAMES, AFFILIATION, ADDRESS, and E-MAIL address of (at least) the contacting author, an ABSTRACT of the submitted paper (less than 500 words), a list of KEYWORDS (no more than 5). The papers should be submitted electronically in PDF (preferred) or postscript format to: mailto:romand at epfl.ch. IMPORTANT DATES: Papers submission: March 31st Acceptance notification: May 7th Final version: June 4th Workshop: August 29th PROGRAM CHAIRS Vincenzo Pallotta (Swiss Federal Institute of Technology - Lausanne, International Computer Science Institute - Berkeley) Amalia Todirascu (University of Troyes and University of Iasi) PROGRAM COMMITTEE Afzal Ballim Alberto Lavelli Alexander Clark Atro Voutilainen Bangalore Srinivas C.J. Rupp Dan Cristea Diego Molle-Aliod Eric Wherli Jose Iria Fabio Massimo Zanzotto Fabio Rinaldi Frank Keller Giovanni Coray G?nther G?rz Hatem Ghorbel Jean-C?dric Chappelier Jean-Pierre Chanod Joachim Niehren John Carroll Kay-Uwe Carstensen Manuela Boros Maria Teresa Pazienza Martin Rajman Michael Hess Patrick Ruch Roberto Basili Rodolfo Delmonte Salah Ait-Mokhtar Susan Armstrong Wolfgang Menzel Yuji Matsumoto LOCAL ORGANIZATION Violeta Seretan (University of Geneva) Hatem Ghorbel (Swiss Federal Institute of Technology - Lausanne) CONTACT INFORMATION: All inquiries should be sent to [romand at epfl.ch]. Please note that general organizational details (registration, accommodation, etc.) are taken care of by COLING 2004, not by the workshop organizers. More information are available the workshop's Web page at http://lithwww.epfl.ch/romand2004/ ------------------------------------------------------------------------- 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 Fri Mar 5 16:59:37 2004 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Fri, 5 Mar 2004 17:59:37 +0100 Subject: Appel: SIGdial04, Demos Message-ID: Date: Thu, 4 Mar 2004 17:06:09 +0100 From: Michael Strube Message-ID: <16455.21489.798775.624253 at eml.villa-bosch.de> X-url: http://sigdial04.eml-research.de ____________________________________________________________________________ Call for Demos 5th SIGdial Workshop on Discourse and Dialogue Cambridge/MA, April 30 and May 1, 2004 (immediately preceding HLT-NAACL) ____________________________________________________________________________ As part of SIGDIAL 04 (http://sigdial04.eml-research.de), we solicit demo presentations of speech and/or natural language systems with discourse or dialog/conversation capabilities. We welcome researchers who wish to present demos using discourse and dialogue in a wide range of efforts (including, for example, corpora annotation, reference resolution systems, discourse act parser, tutorial systems, embodied conversational characters, meeting room agents, spoken language agents interacting via telephone, help agents, humanoid robots conversing with people, etc.). Submission of a 1-2 page description of the demo is required. Submission format: Submissions must be electronic in PDF format and should follow the format of ACL proceedings (except that SIGdial04 demo submissions should include author information since reviewing will not be blind). Authors are strongly encouraged to use the LaTeX style files or MSWord equivalents available on the HLT/NAACL website. Submission procedure: A PDF file of the paper must be uploaded onto the system by March 29, 2004 via the SIGdial04 submission webpage available from http://sigdial04.eml-research.de. Authors who cannot submit a PDF file electronically should contact the program chairs in advance of the paper submission deadline. Authors will not have an opportunity to submit a revised demo description if the demo is accepted, so everyone is advised to provide a submission they consider final. Demo submitters will be notified by April 7th about acceptance of their submissions. No additional documentation will be required. The demo submissions will be collated together as a booklet and provided to all participants at the SIGDIAL '04 meeting. ------------------------------------------------------------------------- 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 Fri Mar 5 17:00:12 2004 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Fri, 5 Mar 2004 18:00:12 +0100 Subject: Appel: Linguistics Workshop on Machine Translation Message-ID: Date: Wed, 03 Mar 2004 00:25:06 +0100 From: "Sylviane CARDEY (Centre Tesni?re)" Message-Id: <3.0.6.32.20040303002506.0180da70 at utinam.univ-fcomte.fr> X-url: http://tesniere.univ-fcomte.fr Appel ? communications Call for papers Appel ? communications aux Journ?es linguistiques " traduction automatique, langues contr?l?es et langues de sp?cialit?s " Comit? scientifique : Haytham Alsharaf (Universit? de Kowe?t) Florence Beaujard (Airbus) Xavier Blanco (Universit? Autonome de Barcelone, Espagne) Christophe Bogachi (Universit? de Varsovie, Pologne) Farouk Bouhadiba (Universit? de Mostaganem, Alg?rie) Sylviane Cardey (Universit? de Franche-Comt?, France) Hui-Lan Chao (Institut Wenzao, Taiwan) Elisa Gavieiro-Villatte (Universit? de Franche-Comt?, France) Yves Gentilhomme (Universit? de Franche-Comt?, France) Peter Greenfield (Universit? de Franche-Comt?, France) Kyoko Kuroda (Shimane College, Japon) Stefan Langer (CIS, Universit? de Munich, Allemagne) Igor Mel'cuk (Universit? de Montr?al, Canada) Ruslan Mitkov (Universit? de Wolverhampton, Angleterre) Elisabeth Ranchhod (Universit? de Lisbonne, Portugal) Laurent.Spaggiari (Airbus France) Comit? d'organisation : Sylviane Cardey, Peter Greenfield, S?verine Vienney (Centre Tesni?re), Universit? de Franche-Comt?, France. Lieu de la manifestation Besan?on, France Date 5-7 mai 2004 Programme prospectif Le programme se composera de 3 grandes sessions Traduction automatique Probl?mes Th?ories Mod?les Outils Applications et d?monstrations Langues contr?l?es Th?ories Mod?les Applications Langues de sp?cialit?s Langues de sp?cialit?s/langues g?n?rales Description Probl?mes Les articles devront s'inscrire dans la probl?matique de l'un ou de plusieurs des th?mes ci-dessus. Un r?sum? d'une page (caract?re 12, interligne 1,5) r?dig? en anglais ou en fran?ais devra parvenir ? ctesniere at univ-fcomte.fr pour le 27 mars 2004 La notification d'acceptation parviendra le 5 avril 2004. Les articles en anglais ou en fran?ais devront parvenir pour le 1er septembre 2004 et seront publi?s dans les actes du colloque (le format sera sp?cifi? ult?rieurement). Call for papers Linguistics Workshop on Machine Translation, Controlled Languages and Specialised Languages Venue: Besan?on, France Dates: 5-7 May 2004 Scientific Committee: Haytham Alsharaf (Kuwait University) Florence Beaujard (Airbus) Xavier Blanco (Autonomous University of Barcelona, Spain) Christophe Bogachi (University of Warsaw, Poland) Farouk Bouhadiba (University of Mostaganem, Algeria) Sylviane Cardey (University of Franche-Comt?, France) Hui-Lan Chao (Wenzao Institute, Taiwan) Elisa Gavieiro-Villatte (University of Franche-Comt?, France) Yves Gentilhomme (University of Franche-Comt?, France) Peter Greenfield (University of Franche-Comt?, France) Kyoko Kuroda (Shimane College, Japan) Stefan Langer (CIS, University of Munich, Germany) Igor Mel'cuk (University of Montr?al, Canada) Ruslan Mitkov (University of Wolverhampton, England) Elisabeth Ranchhod (University of Lisbon, Portugal) Laurent.Spaggiari (Airbus France) Programme Committee: Sylviane Cardey, Peter Greenfield, S?verine Vienney (Centre Tesni?re), University of Franche-Comt?, Besan?on, France Intended Programme The programme will comprise three principal sessions: Machine Translation Problems Theories Models Tools Applications and demonstrations Controlled Languages Theories Models Applications Speciality Languages Speciality languages /general languages Description Problems The papers ought to address one or more of the above themes. A one page abstract (font size 12 point, interline 1.5) in either English or French should be emailed to: ctesniere at univ-fcomte.fr by 27 March 2004. Notification of acceptance: 5 April 2004. Accepted papers, in English or French, should be received by 1st September 2004 and will be published in the workshop's proceedings (the format will be specified later). ----------------------------------------------------------------- Professeur Sylviane CARDEY Directrice du Centre de recherche en linguistique Lucien Tesniere Faculte des Lettres, Email : sylviane.cardey at univ-fcomte.fr 30, rue Megevand, Tel: +33 (0)3 81 66 53 94 25030 BESANCON Cedex, Fax: +33 (0)3 81 66 53 00 FRANCE http://tesniere.univ-fcomte.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 Tue Mar 9 12:04:39 2004 From: thierry.hamon at LIPN.UNIV-PARIS13.FR (Thierry Hamon) Date: Tue, 9 Mar 2004 13:04:39 +0100 Subject: Appel: AMTA-2004 Message-ID: Date: Tue, 9 Mar 2004 00:40:29 +0100 From: Jeff Allen Message-ID: <1078789228.404d046d01d32 at imp3-q.free.fr> X-url: http://www.amtaweb.org/AMTA2004/ X-url: http://www.amtaweb.org/AMTA2004/ X-url: http://www.geocities.com/jeffallenpubs/ X-url: http://www.multilingual.com/machineTranslation62.htm X-url: http://www-lipn.univ-paris13.fr/~hamon/ First Call for Papers and Proposals AMTA-2004 - The 6th Biennial Conference of the Association for Machine Translation in the Americas Location: Georgetown University, Washington DC, USA Dates: September 28 - October 2, 2004 http://www.amtaweb.org/AMTA2004/ Theme: From Real Users to Research Introduction: The previous conference in this series (AMTA 2002) took up the theme "From Research to Real Users" which asked participants to explore why the research conducted on machine translation doesn?t seem to be moving to the marketplace. The past two years have seen the beginnings of change in this, as some research groups with data-driven translation systems are commercializing their work, and rule-based machine translation systems are introducing data-driven techniques to the mix in their products. For this conference, we reverse the question, and take as our theme user needs and explore how or whether market requirements are feeding into research programs. Issues to be addressed: * system customizability, memory requirements, and other issues affecting commercial adoption * integration and customization work * general advances in quality (including: inherent limits on achievable quality? and varying quality by application?) * How are people using MT today? The conference will host the following: * Conference papers (five categories of papers): 1. Research papers 2. MT Users Session 3. MT Research and Deployment Showcase 4. Evolution of Machine Translation 5. System Descriptions/Demonstrations * Tutorials * Roundtable/Panel Sessions * Workshops * Product Exhibition Important Dates: March 30 2004: Submission intention deadline for conference papers (abstract of maximum of 200 words + title + category + author(s) name) April 23 2004: Submission deadline for roundtable/panel sessions Submission deadline for tutorial proposals Submission deadline for technical papers and presentations Submission deadline for workshop proposals May 15 2004: Submission deadline for end user papers and presentations June 11 2004: Notification to authors July 2 2004: Camera-ready copy due July 23 2004: Final papers to publisher All conference details available at: http://www.amtaweb.org/AMTA2004/ Regards, Jeff Allen ******************************************************** Jeff Allen Advisory Board MultiLingual Computing & Technology magazine jeff at multilingual.com or jeff.allen at free.fr New web portal with MT and controlled language publications http://www.geocities.com/jeffallenpubs/ Special supplement of MultiLingual Computing & Technology focused on Machine Translation: http://www.multilingual.com/machineTranslation62.htm ******************************************************** ------------------------------------------------------------------------- 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 Mar 12 12:22:52 2004 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Fri, 12 Mar 2004 13:22:52 +0100 Subject: Conf: EURALEX 2004 Message-ID: Les inscriptions sont maintenat ouvertes pour EURALEX 2004 sur le site : http://www.univ-ubs.fr/euralex2004. EURALEX 2004 Le 11?me congr?s international d'EURALEX aura lieu ? Lorient, France, du 6 au 10 juillet 2004. L'organisateur est la Facult? de Lettres et Sciences Humaines de l'Universit? de Bretagne Sud, Lorient. La venue sera le Paquebot, le b?timent principale de l'Universit?. Contact address Organisateurs du Congr?s EURALEX 2004 Dr. Geoffrey Williams Facult? de Lettres et de Sciences Humaines 4 rue Jean Zay B.P. 92116 56321 Lorient cedex France T?l?phone : (33) 2 97 87 65 31 Fax : (33) 2 97 87 65 25 Email : elx2004 at univ-ubs.fr Website : http://www.univ-ubs.fr/euralex2004 Les renseignements Les informations sur l'h?bergement, les inscriptions et le transport seront tenues ? jour sur ce site. LE CONGRES Le congr?s EURALEX r?unit lexicographes professionnels, ?diteurs, chercheurs, universitaires, et toute personne int?ress?s par les dictionnaires de tous types. Le programme comprendra des conf?rences pl?ni?res, des sessions parall?les sur les th?mes ?num?r?s ci-dessous, des d?monstrations de logiciels, une exposition de livres et de logiciels, et des activit?s de d?tente pour les participants et leurs invit?s. Les th?mes suivants qui sont au centre du congr?s : 1. Lexicographie et Lexicologie Computationnelle 2. Processus d'?laboration des dictionnaires 3. Rapports sur des projets lexicographiques et lexicologiques 4. Lexicographie Bilingue 5. Lexicographie pour Langues de Sp?cialit? Terminologie et Terminographie 6. Lexicographie historique et savante et ?tymologie 7. Utilisation des dictionnaires 8. Phras?ologie et Collocation 9. Questions lexicologiques ayant une pertinence lexicographique 10. Autres th?mes Les conf?rences pl?ni?res seront ? Professor John Sinclair, Tuscan Word Centre ? Dr Pierre Corbin, University of Lille III ? Dr Anthony Cowie, University of Leeds ? Dr Christine Jacquet-Pfau, College de France Le pr?-programme sera publi? bient?t sur le site web. ------------------------------------------------------------------------- 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 Mar 12 12:23:39 2004 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Fri, 12 Mar 2004 13:23:39 +0100 Subject: Appel: ACL workshop : Text Summarization Branches Out Message-ID: Our apologies for multiple postings ------------------------------------------------------------------------ Text Summarization Branches Out July 25-26, 2004. Workshop at ACL 2004 42nd Annual Meeting of the Association for Computational Linguistics Forum Convention Centre Barcelona, Spain http://www.law.kuleuven.ac.be/icri/conferences/acl_summarization2004.php ------------------------------------------------------------------------ Second call for papers Text summarization is still largely in a research phase, and has so far focused on news text, but it is increasingly becoming a tool for information search and selection in a variety of media. For example, summarizing is a necessity when showing content on the screen of a mobile device. Texts integrated in multimedia documents have different genres or types, but they all require the same flexibility in the presentation of summaries by allowing parameterized compression rates and integration in a mixed media format. Text summarization has been so far dominated by statistical techniques. However, for improved output quality and increased compression, other techniques are expected to play important roles as well. Linguistically motivated natural language processing techniques, including semantic analysis and discourse analysis, are almost certainly required for summarization in non-news genres. Automated reasoning techniques could allow fusion and understanding of content. Machine learning, both supervised and unsupervised, still has a major role to play. Finally, evaluation is an ongoing concern. The proposed workshop aims to address all these issues. We invite submission of papers about text summarization including, but not limited to, the following topics. * Single-sentence compression * Multiple-sentence compression and information fusion * Domain-oriented summarization of multiple texts * Comparative summarization of multiple reviews * Summarization of Web pages * Summarization of dialogue (e.g., blogs, video captions) * Summarization of speech * Summarization for mobile devices * Summarization for other disciplines, e.g., legal or medical applications * Toward summarizing large, loosely structured texts (e.g., novels) * Temporal and event semantics for summarization * Data search structures for summaries of flexible and mixed media format * Automated and manual summary evaluation methods * Quantifying summary quality The workshop will feature an invited speaker (to be confirmed), and two panels, one looking back and one looking far ahead, plus ad-hoc discussion groups. Important Dates * Paper submission deadline: March 25, 2004 * Notification of acceptance for papers: April 25, 2004 * Camera ready papers due: May 15, 2004 * Workshop date: July 25-26, 2004 Submission Procedure Authors should submit full papers of maximum 8 pages, including references and figures, following the main conference ACL style format. Submissions should be sent to: http://www.law.kuleuven.ac.be/icri/cyber-chair/html/submit/ Organizing Committee * Eduard Hovy, Information Sciences Institute, University of Southern California, USA * Marie-Francine Moens (co-chair), Interdisciplinary Centre for Law & Information Technology, Katholieke Universiteit Leuven, Belgium * Dragomir Radev, School of Information and Department of Electrical Engineering and Computer Science, University of Michigan, USA * Stan Szpakowicz (co-chair), School of Information Technology and Engineering, University of Ottawa, Canada Program Committee * Regina Barzilay, Computer Science and Artificial Intelligence Lab, MIT, USA * Hercules Dalianis, Royal Institute of Technology, Sweden * Chiori Hori, NTT, Japan * Eduard Hovy, Information Sciences Institute, University of Southern California, USA * Hongyan Jing, IBM T.J. Watson Research Center, USA * Kathy McKeown, Computer Science Department, Columbia University, USA * Chin-Yew Lin, Information Sciences Institute, University of Southern California, USA * Inderjeet Mani, Department of Linguistics, Georgetown University, USA * Daniel Marcu, Information Sciences Institute, University of Southern California, USA * Marie-Francine Moens, Interdisciplinary Centre for Law & Information Technology, Katholieke Universiteit Leuven, Belgium * Dragomir Radev, School of Information and Department of Electrical Engineering and Computer Science, University of Michigan, USA * Horacio Rodriguez, Departamento de LSI, Universitat Politecnica de Catalunya, Spain * Horacio Saggion, Department of Computer Science, University of Sheffield, UK * Judith Schlesinger, IDA/Center for Computing Sciences, USA * Karen Sparck Jones, Computer Laboratory, University of Cambridge, UK * Stan Szpakowicz, School of Information Technology and Engineering, University of Ottawa, Canada * John Tait, School of Computing and Technology, University of Sunderland, UK * Simone Teufel, Computer Laboratory, University of Cambridge, UK * Peter Turney, NRC Ottawa, Canada * Hans van Halteren, Department of Language and Speech, University of Nijmegen, The Netherlands Contact addresses Marie-Francine Moens Interdisciplinary Centre for Law & Information Technology Katholieke Universiteit Leuven Tiensestraat 41 B-3000 Leuven Belgium marie-france.moens at law.kuleuven.ac.be http://www.law.kuleuven.ac.be/icri/staff/staff.php?id=13 Stan Szpakowicz School of Information Technology and Engineering University of Ottawa 800 King Edward Avenue Ottawa, Ontario K1N 6N5 Canada szpak at site.uottawa.ca http://www.site.uottawa.ca/~szpak ------------------------------------------------------------------------- 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 Mar 12 12:24:28 2004 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Fri, 12 Mar 2004 13:24:28 +0100 Subject: Ecole: University of Geneva : School of Translation and Interpretation Message-ID: Dear colleagues, The School of Translation and Interpretation at the University of Geneva delivers three postgraduate degrees in multilingual information processing and terminology. These postgraduate programs (in French), are aimed mainly at translators and interpreters who would like to take advantage of recent advances in multilingual IT. Details are appended below. Please distribute this announcement to concerned people, especially students. A poster (in French) is also available at http://www.unige.ch/eti/courstim/unige-eti-postgrade.pdf With my best regards, Prof. Margaret King, Head of the Multilingual Information Processing Departement ______Description of the postgraduate programs _______ The School of Translation and Interpretation at the University of Geneva delivers three postgraduate degrees in multilingual information processing and terminology: two DESS (dipl?mes d'?tudes sup?rieures sp?cialis?es) and one DEA (dipl?me d'?tudes approfondies). The courses are listed below, in French. The DESS requires at least four modules, followed by an internship period and a DESS thesis. The DEA requires seven modules, followed by a research period, and the writing and defense of a DEA thesis, which may lead to a doctorate. DEA en traitement informatique multilingue (TIM) - Introduction ? la description formelle des langues - Traitement informatique multilingue - Introduction ? la programmation linguistique - Traitement informatique des textes - Fondements th?oriques de la terminologie DESS en terminologie - Principes g?n?raux et m?thodologie de la terminologie - Pratique de la terminologie (I et II) - Terminologie et informatique DESS en traduction assist?e par ordinateur (TAO) - Technologies de l'information et de la communication - Traductique - Technologies de pointe - Traduction automatique - XML pour le traitement informatique multilingue Registration: Applications must be made before March 31, 2004. The procedure is described on the ETI website at http://www.unige.ch/eti (follow 'Admission', then 'DEA/DESS/doctorat'). For more information Please contact Mrs. Doris Schmidt Fourmont, senior student advisor (Doris.Schmidt at eti.unige.ch or +41 22 379 87 07), or see the ETI website at 'Formations' and 'R?glement d'?tudes'. ------------------------------------------------------------------------- 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 Mar 12 12:25:09 2004 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Fri, 12 Mar 2004 13:25:09 +0100 Subject: =?ISO-8859-1?Q?ATALA=3A_journee_du_05/06_=3A_Le_trai?= =?ISO-8859-1?Q?tement_automatique_des_nouvelles_formes_de_co?= =?ISO-8859-1?Q?mmunication_=E9crite?= Message-ID: Journ?e d'Etude de l'ATALA ========================== Le traitement automatique des nouvelles formes de communication ?crite (e-mails, forums, chats, SMS, etc.) Organisateurs ------------- Emilie Guimier De Neef (France Telecom R & D) Jean V?ronis (Universit? de Provence) Conf?rencier invit? ------------------- Jacques Anis, Universit? Paris X Date ---- 5 juin 2004 Lieu ---- ENST, 46, rue Barrault ou 49, rue Vergnault, 75013 Paris M?tro : Corvisart Th?me ----- Depuis quelques ann?es on assiste ? une v?ritable explosion de nouvelles formes de communication ?crite (NFCE) : e-mails, forums, chats, SMS, etc. Le d?veloppement de passerelles entre les diff?rents m?dias (les e-mails et les SMS s'?coutent) ainsi que la n?cessit? de faciliter la gestion des contenus (classification automatique des e-mails, recherche d'informations...) am?nent de plus en plus de technologies du TAL ? s'appliquer aux NFCE : synth?se de la parole, filtrage et classification automatique, d?tection automatique de mots-cl?s et de th?mes, traduction automatique, etc. Or, les NFCE montrent une grande d?viance par rapport ? l'?crit plus ou moins norm? que le TAL a l'habitude de traiter. Si on laisse de c?t? les probl?mes de composition pos?s par les e-mails (renvois successifs, compl?tion progressive des messages) pour ne conserver que les aspects proprement linguistiques pos?s par les NFCE, on observe d'une part des ph?nom?nes que l'on pourrait regrouper sous le terme de "rat?s" (erreurs orthographiques et typographiques, absence de s?parateur entre les mots etc.) qui doivent leur origine au mode de communication souvent direct ou semi-direct, ? la rapidit? de composition du message ou aux contraintes de saisies impos?es par le clavier utilis? (terminal mobile)... Mais on constate d'autre part une v?ritable ?mergence de nouveaux modes d'?criture (abr?viations, smileys, ?criture "texto", etc.), au milieu d'une tr?s grande variabilit? et d'une cr?ativit? constante. Ce qui semble caract?ristique des NFCE, c'est que les utilisateurs inventent en permanence de nouveaux proc?d?s. Enfin, des caract?ristiques fortement dialogiques rendent les NFCE interm?diaires d'une certaine fa?on entre l'?crit "classique" et l'oral : les e-mails se citent, les chats conversent. Paradoxalement, on note peu de publications en TAL sur le sujet, qui a surtout ?t? abord? sous l'angle de la sociologie et de la communication. Les difficult?s qui se posent aux syst?mes de TAL sont immenses, m?me pour ceux qui ont atteint une certaine maturit? sur l'?crit classique (?tiqueteurs morpho-syntaxiques, etc.). Elles aboutissent le plus souvent ? une d?gradation consid?rable des performances, rendant souvent leur utilisation presque impossible en pratique. Le but de la journ?e est de r?unir des chercheurs autour des probl?mes li?s au traitement linguistique des nouvelles formes de communication ?crite : - ponctuation absente ou exag?r?ment utilis?e - typographie d?viante - erreurs orthographiques massives - mode de cr?ation des abr?viations - phon?tisation de l'?criture - nouvelles marques d'expressivit? et d'?motion - aspects dialogiques - diff?rences linguistiques profondes (usage des temps, etc.) Cette liste n'est pas limitative. Soumission ---------- Un r?sum? de deux ? quatre pages doit ?tre envoy? avant le 5 mai 2004 par courrier ?lectronique, en format RTF ou TXT uniquement ? Emilie Guimier De Neef ou Jean V?ronis Les notifications d'acceptation seront envoy?es le 15 mai 2004. Pour plus d'informations sur l'ATALA et sur l'organisation des journ?es d'?tudes, consultez le site de l'ATALA ? l'adresse : http://www.atala.org ------------------------------------------------------------------------- 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 Mar 12 12:31:46 2004 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Fri, 12 Mar 2004 13:31:46 +0100 Subject: Conf : Controlled Language seminar at the Society for Technical Communication Message-ID: Controlled Language seminar at the Society for Technical Communication (STC) France Chapter meeting. Date: 2 April 2004 Location: Holiday Inn Hotel, Paris, France, 19th arrondissement. Invited speakers: Jeff Allen (Mycom France and MultiLingual Computing & Technology) Kathy Barthe (Airbus) More information and registration form available in the "Controlled Language and Machine Translation Events" section at: http://www.geocities.com/controlledlanguage/ Regards, Jeff ******************************************************** Jeff Allen Advisory Board MultiLingual Computing & Technology magazine jeff at multilingual.com or jeff.allen at free.fr New web portal (including MT and CL publications) http://www.geocities.com/jeffallenpubs/ ******************************************************** ------------------------------------------------------------------------- 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 Thu Mar 18 07:35:42 2004 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Thu, 18 Mar 2004 08:35:42 +0100 Subject: ATALA: journee du 15/05 : Evaluation et analyseurs syntaxiques Message-ID: Samedi 15 mai 2004 EVANS :"'?valuation et analyseurs syntaxiques" Journ?e organis?e par Patrick Paroubek , Isabelle Robba et Anne Vilnat(LIMSI - CNRS) Appel ? contribution Depuis une dizaine d'ann?es, avec l'apparition des outils de recherche d'information sur le web, de nouvelles techniques d'analyse syntaxique plus robustes ont vu le jour. Les analyseurs partiels construisent une analyse parfois minimale, incompl?te, mais cela quels que soient lataille et le contenu des donn?es ? traiter. Dans le m?me temps, les analyseurs qui tentent de produire syst?matiquement une analyse "compl?te", ou la plus compl?te possible ont continu? d'am?liorer leurs r?sultats. Pour aider au d?veloppement de ces analyseurs, mais aussi pour permettre la comparaison de leurs performances, il est important de disposer des m?thodes et des outils permettant de les ?valuer. Et la mise en oeuvre de ces m?thodes suppose plusieurs ?tapes qui sont: * la d?finition d'un format d'annotation permettant une large couverture des ph?nom?nes syntaxiques ; * le choix d'un corpus et son annotation manuelle (ou semi-automatique) dans ce format d'annotation ; * la d?finition d'un ensemble de mesures permettant l'?valuation ; * la mise au point des outils aussi bien d'annotation, que de transcription et d'?valuation. De nombreux pays ont commenc? ? s'int?resser ? l'?valuation. Des discussions ont eu lieu sur les annotations ? produire, sur les m?thodes pour les obtenir et des corpus annot?s dans diff?rentes langues ont ?t? peu ? peu constitu?s : que ce soit en anglais (voir le c?l?bre Penn TreeBank et sa "derni?re" couche le Propbank) mais aussi et peut-?tre surtout dans un certain nombre de langues ? moins forte diffusion, comme le bulgare (BulTreeBank), le tch?que (PDT), le norv?gien, le su?dois, le finlandais, le danois (Arboretum), le catalan, le basque et l'espagnol (3LB), l'allemand (Negra, T?Ba-D). En ce qui concerne l'anglais, qui est sans doute la langue pour laquelle les recherches ?taient les plus avanc?es, les m?triques et les corpus annot?s dans le cadre de la campagne PARSEVAL sont aujourd'hui remis en cause car ils ne sont ouverts ni ? d'autres langues ni ? de nouveaux formats d'analyse (voir l'atelier de la conf?rence LREC 2002 : Beyond Parseval towards improved evaluation measures for parsing systems). Ce qui nous montre que la probl?matique de l'?valuation des analyseurs syntaxiques n'est en rien r?solue et donc est ouverte ? toute nouvelle proposition. Pour le fran?ais, la campagne d'?valuation EVALDA/EASY du programme Technolangue, ? l'initiative du minist?re d?l?gu? ? la recherche et aux nouvelles technologies) a d?but? en janvier 2003. Elle sert de lieu d'exp?rimentation pour tester de nouvelles approches pour l'?valuation des analyseurs syntaxiques du fran?ais. Le but de cette journ?e sera donc de d?velopper une r?flexion autour des m?thodologies d'?valuation, des corpus, des m?triques, des outils et des formalismes d'annotation. Conf?rencier invit?: John Carroll, de l'Universit? du Sussex, donnera une conf?rence invit?e lors de cette journ?e : "Evaluating parsers using decomposed and weighted representations" Les contributions attendues pourront porter sur l'un des th?mes suivants : * l'annotation des corpus (formalisme, outils, ...) * les corpus * les m?thodologies d'?valuation * les m?triques d'?valuation (choix, outils ...) * les outils de projection d'un analyseur dans un formalisme Des articles prospectifs sur l'?valuation et les analyseurs syntaxiques seront ?galement les bienvenus. Organisateurs : Patrick Paroubek, Isabelle Robba et Anne Vilnat Format des soumissions : R?sum?s longs ou articles courts entre 2 et 4 pages. Les soumissions devront se faire sous format ?lectronique de pr?f?rence, en version pdf, ou ps. Les r?sum?s devront ?tre envoy?s ? : evans at limsi.fr. En cas de probl?me, vous pouvez ?galement transmettre une version papier, adress?e aux organisateurs, au : LIMSI, BP133, 91403 Orsay Cedex Comit? Scientifique * Veronique Gendner (LIMSI-CNRS) * Laura Monceaux (LINA - Univ. Nantes) * Patrick Paroubek (LIMSI-CNRS) * Isabelle Robba (LIMSI-CNRS) * Anne Vilnat (LIMSI-CNRS) * Salah Ait-Mokhtar (XRCE-XEROX) Calendrier: * 13/04/04 - date limite pour la soummission des articles * 30/04/04 - notification aux auteur * 15/05/04 - journee Pour plus d'informations sur l'ATALA et sur l'organisation des journ?es d'?tudes, consultez le site de l'ATALA ? l'adresse : http://www.atala.org ou le site de la journee http://www.limsi.fr/Recherche/CORVAL/atala_evans ------------------------------------------------------------------------- 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 Thu Mar 18 07:35:47 2004 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Thu, 18 Mar 2004 08:35:47 +0100 Subject: Conf: 5th SIGdial Workshop on Discourse and Dialogue Message-ID: ____________________________________________________________________________ SIGdial '04 News 5th SIGdial Workshop on Discourse and Dialogue Cambridge/MA, April 30 and May 1, 2004 (immediately preceding HLT-NAACL) ____________________________________________________________________________ PROGRAM The program for the SIGdial '04 workshop is available on the SIGdial '04 homepage (http://sigdial04.eml-research.de). Follow the link to "Program". ____________________________________________________________________________ CALL FOR DEMOS The deadline for demo submissions is March 29, 2004. We solicit demo presentations of speech and/or natural language systems with discourse or dialog/conversation capabilities. We welcome researchers who wish to present demos using discourse and dialogue in a wide range of efforts (including, for example, corpora annotation, reference resolution systems, discourse act parser, tutorial systems, embodied conversational characters, meeting room agents, spoken language agents interacting via telephone, help agents, humanoid robots conversing with people, etc.). See http://sigdial04.eml-research.de and follow the link to "Call for Demos". ____________________________________________________________________________ REGISTRATION Online registration for SIGdial '04 is available on the HLT/NAACL website (http://www.aclweb.org/hltnaacl04reg/hltnaacl04reg.php). ____________________________________________________________________________ STUDENT VOLUNTEEERS We are looking for student volunteers who would help at the registration desk (among other duties) in exchange for free registration. This is not a full-time job but you may miss a session or two. Please don't register but contact us at sigdial04 at eml-research.de. ------------------------------------------------------------------------- Message diffus? par la liste Langage Naturel Informations, abonnement : http://www.biomath.jussieu.fr/LN/LN-F/ English version : http://www.biomath.jussieu.fr/LN/LN/ Archives : http://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 Thu Mar 18 07:35:50 2004 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Thu, 18 Mar 2004 08:35:50 +0100 Subject: Conf: Text Summarization Branches Out : DEADLINE CHANGES Message-ID: [A new paper submission deadline -- apologies for reposting.] Text Summarization Branches Out Workshop at the 42nd Annual Meeting of the Association for Computational Linguistics Forum Convention Centre, Barcelona, Spain July 25-26, 2004 http://www.law.kuleuven.ac.be/icri/conferences/acl_summarization2004.php ---------------- The announcement posted on March 12 asked for submissions by March 25, 2004. The new dates are as follows: * Paper submission deadline: April 1, 2004 * Notification of acceptance: April 25, 2004 * Camera-ready papers due: May 15, 2004 ------------------------------------------------------------------------- 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 Thu Mar 18 07:35:54 2004 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Thu, 18 Mar 2004 08:35:54 +0100 Subject: Ecole: linguistique de corpus: constitution, archivage, evaluation Message-ID: ECOLE Th?matique linguistique de corpus: constitution, archivage, ?valuation Lieu : Universit? de Caen, campus 2, D?partement d'informatique Dates : 14-19 juin 2004 Dur?e : 6 jours Nombre total de participants : 56 H?bergement en cit? universitaire SITE DE L'ECOLE THEMATIQUE : http://www.crisco.unicaen.fr/ELC IMPORTANT: DATE LIMITE DE DEPOT DES CANDIDATURES LE 30 AVRIL 2004 (voir fiche d'inscription sur le site) PUBLIC CONCERNE : Les chercheurs du d?partement SHS et du d?partement STIC (domaine IHM) du CNRS ainsi que les enseignants-chercheurs et doctorants en linguistique th?orique et appliqu?e. THEME : Pr?sentation et manipulation des m?thodes et outils qui permettent la recherche et l'analyse critique de donn?es linguistiques tant ? l'oral qu'? l'?crit avec l'aide des technologies de l'information. SITUATION SCIENTIFIQUE : Le d?veloppement de la linguistique de corpus ne cesse de cro?tre depuis les ann?es 1990 (ressources informatis?es volumineuses, essor des ouvrages sur la linguistique de corpus, cr?ation r?cente de l'ILF, int?gration des cours de linguistique de corpus dans les formations universitaires). Parall?lement, le dialogue entre informaticiens et linguistes reste frileux. Un d?cloisonnement de ces disciplines s'av?re fondamentalement n?cessaire. Cette Ecole sera conduite dans un cadre interdisciplinaire o? se c?toieront principalement informaticiens, ing?nieurs, linguistes et juristes. CONS?QUENCES ATTENDUES : D?velopper une synergie en linguistique de corpus au sein des laboratoires des participants, doter les chercheurs en linguistique th?oriques d?un r?elle autonomie, partager les exp?riences et conna?tre les besoins sp?cifiques des laboratoires. GRANDS AXES DU PROGRAMME : Aspects th?oriques et m?thodologiques des corpus (constitution, corpus de r?f?rence, corpus communs, m?ta-donn?es, codage, m?trique). Aspects pratiques (cr?ation et archivage, enrichissements, outils de requ?tes et de calcul). MODALITES PEDAGOGIQUES : Alternance de cours th?oriques et de situations pratiques. MOTS CLES : LINGUISTIQUE CORPUS TIC (Techniques d'Information et de Communication) ARCHIVAGE Inscriptions 100 euros 45 euros pour les ?tudiants gratuit pour les agents CNRS Responsable scientifique Anne LACHERET-DUJOUR, Universit? de Caen TEl. : 02 31 56 56 27 - Fax : 02 31 56 54 27 - E mail : anne.lacheret at crisco.unicaaen.fr Responsable r?gional du projet pour la formation permanente: Emmanuel Mettereau D?l?gation R?gionale : Normandie TEL : 02 31 43 45 37 - Fax 02 31 43 45 06 E mail : meterreau at dr19.cnrs.fr Comit? scientifique Catherine Camugli-Gallardo CRISCO Jacques Fran?ois CRISCO Beno?t Habert LIMSI Anne Lacheret-Dujour CRISCO Thomas Lebarb? LIDILEM Franck Neveu CRISCO Anne Nicolle GREYC Laurent Romary LORIA Comit? d'organisation Catherine Camugli-Gallardo CRISCO Jacques Fran?ois CRISCO Anne Lacheret-Dujour CRISCO Thomas Lebarb? GREYC S?bastien Monnier CRISCO Anne Nicolle GREYC Emmanuel Meterreau D?l?gation Normandie ------------------------------------------------------------------------- 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 Thu Mar 18 07:36:02 2004 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Thu, 18 Mar 2004 08:36:02 +0100 Subject: Jobs: Research Positions in Tarragona Message-ID: 2 Research Positions at the Research Group on Mathematical Linguistics, Rovira i Virgili University, Tarragona, Spain Funded by the Spanish Ministry for Science and Technology and Rovira i Virgili University Position 1: for scholars having up to 10 years of postdoc experience Position 2: for scholars having up to 3 years of postdoc experience Duration: 5 year-contract starting in Autumn 2004 Salary position 1: 30,000 euros/year (before taxes) + up to 12,000 euros for expenses (in the first two years) + full Social Security coverage Salary position 2: 23,000 euros/year (before taxes) + full Social Security coverage Research topics: formal language theory and any of its application areas Deadline position 1: March 5, 2004 Deadline position 2: March 22, 2004 Expressions of interest position 1: until February 27, 2004 Expressions of interest position 2: until March 12, 2004 Contact: cmv at astor.urv.es Website: http://pizarro.fll.urv.es/continguts/linguistica/proyecto/grlmc.htm -------------------------------------------------------------------------------------------------- Carlos Martin-Vide Head, Research Group on Mathematical Linguistics Head, Department of Romance Philologies Rovira i Virgili University Pl. Imperial Tarraco, 1 43005 Tarragona, Spain phone: +34-977559543 fax: +34-977559597 e-mail: cmv at astor.urv.es http://pizarro.fll.urv.es/continguts/linguistica/proyecto/grlmc.htm ------------------------------------------------------------------------- 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 Thu Mar 25 16:49:58 2004 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Thu, 25 Mar 2004 17:49:58 +0100 Subject: Appel: COLING Workshop : INTERNATIONAL JOINT WORKSHOP ON NLP IN BIOMEDECINE Message-ID: SECOND CALL FOR PAPERS COLING Workshop INTERNATIONAL JOINT WORKSHOP ON NATURAL LANGUAGE PROCESSING IN BIOMEDICINE AND ITS APPLICATIONS (BioNLP/NLPBA 2004) http://www.genisis.ch/~natlang/JNLPBA04/ Call for Papers http://www.genisis.ch/~natlang/JNLPBA04/cfp.html Geneva, Switzerland August 28-29, 2004 ** Regular papers deadline: 14th April ** ** Shared task paper deadline: 21st April ** Workshop Description Recent years have seen a growing interest in the application of NLP techniques to texts in the domains of biology and medicine. The problem of information overload that has resulted from the massive growth in the scientific literature has clearly shown the necessity to automatically locate, organize and manage facts relating to experimental results. At the same time clinicians have experienced greatly improved access to the medical literature and clinical repositories which needs to be matched by the development of enhanced information access tools. This year NLPBA (http://www.genisis.ch/~natlang/NLPBA02/) and BioNLP (http://www-tsujii.is.s.u-tokyo.ac.jp/ACL03/bionlp.htm) merge for a joint workshop with the aim of bringing together researchers from natural language processing, bio-informatics, medicine and ontologies who are concerned with developing methods and resources for solving these problems. Over the last five years we have seen significant steps forward in the development of language technology and large-scale resources for the Bio-Medical domain such as linguistically annotated corpora (e.g. GENIA POS and NE corpora), ontologies (e.g. Gene Ontology), thesauri (e.g. UMLS Metathesaurus), lexicons and term lists (e.g. UMLS SPECIALIST) as well as information retrieval collections (e.g. TREC Genomics track). At the application level we see development of question answering systems, event recognition, zone (rhetorical region) identification, as well as term and bio-entity recognition. The demand for information access tools from domain users is increasing to support literature survey, often integrated into online portals where scientists can navigate through related information resources such as genetics and disease databases. Ongoing challenges relate to the growing and ambiguous nomenclature, the need to integrate deep knowledge sources into machine learning, a need to scale up methods for processing full text articles etc. The objective of the workshop is to bring together researchers in this area, to establish common themes and goals between different groups. We have seen from previous experience in the natural language learning and information retrieval communities the benefits of sharing resources and developing common evaluation criteria. In this workshop we are introducing a special shared task to promote discussion of these issues as well as the objective of integrating machine learning with knowledge resources. We invite submission of papers on topics related to bio-medical NLP including, but not limited to: * Information extraction * Text mining * Named entity recognition * Coreference resolution * Term recognition * Knowledge-based information retrieval * Multi-lingual resources and applications * Ontology construction and ontology mapping * Visualization tools for viewing clustered or extracted information or meta-data * Multi-modal approaches combining text and images, etc. * Event recognition * Construction of pathways from literature and databases * Creation of data-sets of bio-medical entities, coreferences and relations * Annotation standards and quality control methodologies * Resource integration and re-engineering * Corpus/lexicon construction * Text summarization and report generation Shared Task http://research.nii.ac.jp/~collier/workshops/JNLPBA04st.htm This year we propose to have a special shared task: bio-medical named entity recognition from the GENIA corpus. The purpose of this track is essentially to investigate the integration of statistical machine learning methods with symbolic knowledge sources from the bio-medical domain such as ontologies, thesauri and lexicons : shared task description. Invited Speaker To be announced soon Paper Format and Submission Papers must follow the COLING 2004 templates, and will be submitted by email to jnlpba-submit at sim.hcuge.ch. Regular papers should follow the COLING 2004 templates for regular papers (i.e. at most 7 pages) and shared task papers should be formatted as per the COLING project notes style (4 pages) focussing in particular on method, results and discussion. Important Dates Submission deadline for regular workshop papers: April 14th, 2004 Submission deadline for shared task papers: April 21st, 2004 Notification of accepted papers: May 14th, 2004 Deadline for camera ready copies: June 6th, 2004 Workshop Chairs Nigel Collier (National Institute of Informatics, Japan) Patrick Ruch (University Hospital of Geneva and EPFL, Switzerland) Adeline Nazarenko (LIPN, France) Organizing Committee Alfonso Valencia (Centro Nacional de Biotecnologia, Spain) Carol Friedman (CUNY/Columbia University, USA) Donia Scott (University of Brighton, UK) Udo Hahn (Albert-Ludwigs University, Freiburg, Germany) Junichi Tsujii (University of Tokyo, Japan) Program Committee Sophia Ananiadou (University of Salford, UK) Alan Aronson (National Library of Medicine, USA) Robert Baud (University Hospital of Geneva, Switzerland) Christian Blaschke (CNB, Spain) Oliver Bodenreider (National Library of Medicine, USA) Berry de Bruijn (National Research Center, Canada) Marc Craven (University of Wisconsin, USA) Robert Gaizauskas (University of Sheffield, UK) Eric Gaussier (Xerox, XRCE, France) Vasileios Hatzivassiloglou (Columbia University, USA) Lynette Hirschman (MITRE, USA) Dimitar Hristovski (University of Ljubljana, Slovenia) Jerry Hobbs (USC/ISI, USA) Aravind Joshi (University of Pennsylvania, USA) Su Jian (Institute for Infocomm Research, Singapore) Asao Fujiyama (National Institute of Informatics, Japan) Arne Jonsson (University of Linkoping, Sweden) Frederique Lisacek (GeneBio SA, Switzerland) Yuji Matsumoto (NAIST, Japan) Claire Nedellec (INRA, France) Kousaku Okubo (Kyushu University, Japan) Jong C. Park (KAIST, Korea) Thierry Poibeau (LIPN, France) Denys Proux (Xerox, XRCE, France) James Pustejovsky (Brandeis University, USA) Dietrich Rebholz-Schuhmann (European Bioinformatics Institute, EU) Irena Spasic (UMIST, UK) Ben Stapley (UMIST, UK) Padmini Srinivasan (University of Iowa, USA) Hirotoshi Taira (NTT Communication Science, Japan) Toshihisa Takagi (University of Tokyo, Japan) Yuka Tateishi (University of Tokyo, Japan) Anne-Lise Veuthey (SIB, Switzerland) Limsoon Wong (Institute for Infocomm Research, Singapore) Pierre Zweigenbaum (AP-HP, INSERM & INaLCO, France) Shared Task Committee Nigel Collier (National Institute of Informatics, Japan) Jindong Kim (University of Tokyo, Japan) Yuka Tateisi (University of Tokyo, Japan) Tomoko Ohta (University of Tokyo, Japan) Yoshimasa Tsuruoka (University of Tokyo, Japan) Contact Information General organization : jnlpba-request at sim.hcuge.ch Shared task organization: bio04sharedtask at nii.ac.jp Main page : http://www.genisis.ch/~natlang/JNLPBA04/ ------------------------------------------------------------------------- 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 Thu Mar 25 17:20:39 2004 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Thu, 25 Mar 2004 18:20:39 +0100 Subject: Soft: Flemm v31 Message-ID: (Version Fran?aise) (English version : see below) ===================================================================== Flemmv31 - Analyseur morphologique Flexionnel du Fran?ais - version 3.1 Fiammetta Namer ===================================================================== FLEMMv3.1 est un ensemble de modules Perl5 qui effectue l'analyse flexionnelle des formes fl?chies de textes en fran?ais qui ont ?t? au pr?allable ?tiquet?s, au moyen de l'un des deux cat?gorisateurs : Brill ou TreeTagger. C'est un petit programme (60kb au format zipp?, ? l'exclusion des programmes et corpus test), principalement bas? sur l'usage de r?gles (un lexique de 3000 mots seulement est utilis? pour prendre en compte les exceptions). Il fonctionne sur PC ou station de travail, sous Unix, Linux ou Windows9x/NT/XP. T?l?chargement : http://www.univ-nancy2.fr/pers/namer/Telecharger_Flemm.html Caract?ristiques et changements par rapport ? la version 3.0 : - mise ? jour par rapport au nouveau jeu d'?tiquettes de TreeTagger (3.1) - r?sultats con?us sous forme d'APIs en Perl - modules enti?rement document?s (voir fonction perldoc) - traits flexionnels format?s selon les recommandations de Multext - deux modes d'affichage possibles des r?sultats : mode lin?aire, et format XML. (Pour plus de d?tails, voir URL ci-dessus) ===================================================================== (English Version) ===================================================================== Flemmv31 - Inflectional morphology parser for French - version 3.1 Fiammetta Namer ===================================================================== FLEMMv3.1 is a Perl5 set of modules that performs inflectional analysis on French texts which have previously been tagged (i.e. by either the TreeTagger or the Brill tagger). This is a small program, (60kb in a zipped format, excluded the test programs and corpora) mainly rule-based (i.e. only a 3000 words lexicon is used in order to deal with exceptions). It runs on PCs or Workstation, under Unix, Linux or Windows9x/NT/XP OS. Downloading : http://www.univ-nancy2.fr/pers/namer/Telecharger_Flemm.html Charcateristics and changes wrt version 3.0 : - updating according to the new Treetagger tagset (3.1) - results designed as perl APIs - fully documented modules (see perldoc function) - inflectional features formatted according to the Multext norm. - two possible displays of the results : either linear or xml formats. (see details at the URL given above) ===================================================================== ------------------------------------------------------------------- Fiammetta NAMER Universit? Nancy 2 / U.F.R. Sciences Du Langage UMR 7118 "ATILF" Bureau B05 23 Boulevard Albert 1er B.P. 33 97 54000 Nancy - France T?l?phone : (33) 03 83 96 71 93 URL : http://www.univ-nancy2.fr/pers/namer E-mail : Fiammetta.Namer at univ-nancy2.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 Amalia.Todirascu at LORIA.FR Mon Mar 29 15:52:43 2004 From: Amalia.Todirascu at LORIA.FR (Amalia.Todirascu at LORIA.FR) Date: Mon, 29 Mar 2004 13:52:43 -0200 Subject: Last CFP: COLING'04 Workshop on RObust Methods in Analysis of Natural language Data Message-ID: LAST CALL FOR PAPER Submission Deadline: March 31st ROMAND 2004 3rd workshop on RObust Methods in Analysis of Natural language Data A satellite event of COLING 2004 Geneva - August 29th 2004 http://lithwww.epfl.ch/romand2004/ Robustness in Computational Linguistics has been recently recognized as a central issue for the design of interactive applications based on natural language communication. If a failure of the system can be acceptable in batch applications requiring a human intervention, an on-line system should be capable of dealing with unforeseen situations in a more flexible way. When we talk about system failure we do not think at inherent program failures like infinite loops or system exception, we consider, rather, failures related to the processing of the input and its assimilation in the system's knowledge base. A failure of this kind means simply that the system does not "understand" the input. The automated analysis of natural language data has become a central issue in the design of Intelligent Information Systems. Processing unconstrained natural language data is still considered an AI-hard task. However, various analysis techniques have been proposed in order to address specific aspects of natural language. In particular, recent interest has been focused on providing approximate analysis techniques, assuming that when perfect analysis is not possible, partial results may be still very useful. ROMAND 2004 is the third of a series of workshops aimed at bringing together researchers and students that work in fields like artificial intelligence, computational linguistics, human-computer interaction, cognitive science and are interested in robust methods in natural language processing and understanding. The term "natural language" is intended as all the possible modalities of human communication and it is not restricted to written or spoken language. Theoretical aspects of robustness in Natural Language Processing (NLP) and Understanding (NLU) are welcome as well as engineering and industrial experiences. We are also interested in research works that investigate different types of linguistic modules integration, in order to characterise their advantages and disadvantages with respect to different types of applications, and works that propose different types of NLP/NLU systems, ranging from sequential/pipelined architectures to more loosely-coupled multi-level distributed architectures. We invite papers on all topics related to robustness in natural language processing, including, but not limited to: * Natural Language Architectures * Robust Morpho-Syntactic Parsing * Robust Semantics * Robust Discourse Analysis * Robust Computational Pragmatics * Complexity of linguistic analysis * Spell checking and automated spell correction * NLP and Soft Computing * Hybrid methods in computational linguistics * Information Extraction * Multimedia Document Analysis * Spoken Language Understanding * Multimodal Human-Computer Interfaces * Cognitive Linguistics INVITED TALKS Dr. Frank Keller, University of Edinburgh: "Gradient Grammaticality: Applications in Robust Parsing" SUBMISSION PROCEDURE: Authors should submit an anonymous paper (avoiding, as much as possible, hints for the identification of authors) of at most 10 pages (including pictures and references), intended for talks with a duration of minutes plus 10 minutes for discussions. The paper should follow the COLING formatting style available on the main conference web site (http://www.issco.unige.ch/coling2004/), and the authors must also send us a wrapper e-mail message indicating: 1. the AUTHOR'S NAMES, AFFILIATION, ADDRESS, and E-MAIL address of (at least) the contacting author, 2. an ABSTRACT of the submitted paper (less than 500 words), 3. a list of KEYWORDS (no more than 5). The papers should be submitted electronically in PDF (preferred) or postscript format to: mailto:romand at epfl.ch. IMPORTANT DATES: Papers submission: March 31st Acceptance notification: May 7th Final version: June 4th Workshop: August 29th PROGRAM CHAIRS Vincenzo Pallotta (Swiss Federal Institute of Technology - Lausanne and International Computer Science Institute - Berkeley) Amalia Todirascu (University of Troyes and University of Iasi) PROGRAM COMMITTEE Afzal Ballim Alberto Lavelli Alexander Clark Atro Voutilainen Bangalore Srinivas C.J. Rupp Dan Cristea Diego Molla'-Aliod Eric Wherli Jose' Iria Fabio Massimo Zanzotto Fabio Rinaldi Frank Keller Giovanni Coray Guenther Goerz Hatem Ghorbel Jean-Cedric Chappelier Jean-Pierre Chanod Joachim Niehren John Carroll Kay-Uwe Carstensen Manuela Boros Maria Teresa Pazienza Martin Rajman Michael Hess Patrick Ruch Roberto Basili Rodolfo Delmonte Salah Ait-Mokhtar Susan Armstrong Wolfgang Menzel Yuji Matsumoto LOCAL ORGANIZATION Violeta Seretan (University of Geneva) Hatem Ghorbel (Swiss Federal Institute of Technology - Lausanne) CONTACT INFORMATION: All inquiries should be sent to [romand at epfl.ch]. Please note that general organizational details (registration, accommodation, etc.) are taken care of by COLING 2004, not by the workshop organizers. More information are available the workshop's Web page at http://lithwww.epfl.ch/romand2004/ ------------------------------------------------------------------------- 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 Mar 30 09:54:59 2004 From: alexis.nasr at LINGUIST.JUSSIEU.FR (alexis.nasr at LINGUIST.JUSSIEU.FR) Date: Tue, 30 Mar 2004 11:54:59 +0200 Subject: Conf: TALN 2004 : Atelier QUESTION-REPONSE Message-ID: ********************************************************************** Dans le cadre de la conf?rence T A L N 2 0 0 4 Atelier QUESTION-REPONSE http://www.lpl.univ-aix.fr/jep-taln04/question-answer.htm Palais de Congr?s F?s (Maroc) Le 22 avril 2004 ********************************************************************** Programme 9h - 10h - Conf?rence invit?e Automatic Induction of Text Entailment Patterns for Question Answering Bernardo Magnini, ITC-IRST, Trento, Italie 10h - 11h Deux pistes compl?mentaires pour am?liorer l'appariement Question R?ponse Karine Lavenus, Jens Grivolla, Laurent Gillard, Patrice Bellot, LIA, Avignon Filtering Out Bad Answers with Semantic Relations in a Web-Based Question-Answering System Leila Kosseim and Jamileh Yousefi, CLaC lab., Concordia University, Montreal, Canada Ressources pour un Syst?me de Question/R?ponse Eric Crestan, Elise Lemaire, Claude de Loupy, Sinequa, Ivry-sur-Seine, LIA, Avignon, MoDyCo, Nanterre 11h - 11h30 - pause 11h30 - 12h30 Using semantic information to improve the performance of a restricted-domain question-answering system Hai Doan-Nguyen and Leila Kosseim, CLaC lab., Concordia University, Montreal, Canada The importance of How-questions in technical domains Rolf Schwitter, Fabio Rinaldi, Simon Clematide, Macquarie University, Sydney, Australie et University of Zurich 12h30 - 14h - pause d?jeuner 14h - 15h G?n?ration de requ?tes pour les syst?mes de Q/R avec un mod?le d'apprentissage statistique Nicolas Usunier, Massih Reza Amini, Patrick Gallinari, Brigitte Grau, LIP6, Paris et LIMSI, Orsay L'analyse des questions : int?r?ts pour la g?n?ration des r?ponses Sara Mendes, V?ronique Moriceau, CLUL, Lisbonne et IRIT, Toulouse 15h - 15h20 - pause 15h20 - 16h Pr?sentation de EQUER, la campagne d'?valuation des syst?mes de question-r?ponse sur le fran?ais. EQUER fait partie du projet Technolangue EVALDA sous la responsabilit? de ELDA Maria Nava, ELDA Discussion -- Groupe LIR - LIMSI BP 133, 91403 Orsay Cedex tel. 01 69 85 80 03, fax 01 69 85 80 88 et Institut d'Informatique d'Entreprise (IIE) 18 all?e Jean Rostand, 91025 Evry Cedex tel. 01 69 36 73 44, fax 01 69 36 73 09 mail : grau at iie.cnam.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/ -------------------------------------------------------------------------