The publications database contains papers and technical reports written by XRCE scientists from 1991 up to the present. If the document you are looking for cannot be downloaded in PDF or Postscript format, please write to webmaster@xrce.xerox.com specifying the title, author(s) and reference. Any document downloaded from the publications database may be used for non-commercial purposes only.

• Year 2006

  Acronym-meaning extraction from corpora using multitape weighted finite-state machines Andre Kempe Abstract | report.pdf (66.7KB) Research Report Ref. : 2006/019 Automatic evaluation of machine translation quality Cyril Goutte Abstract | MTeval.pdf (76.38KB) Presentation at the European Community Ref. : 2006/002 Categorisation in multiple category systems Gabriela Csurka, Eric Gaussier, Cyril Goutte, Francois Pacull, Jean-Michel Renders Abstract | 2006-012.pdf (144.42KB) International conference on machine learning, (ICML) Pittsburgh, Pennsylvania, June 25-29, 2006. Ref. : 2006/012 Lexical entailment for information retrieval Stéphane Clinchant, Cyril Goutte, Eric Gaussier Abstract | xrce_entailment.pdf (118.33KB) European Conference on Information Retrieval, London, UK, 10-12 April 2006. Ref. : 2005/064 Multitape automata with symbol classes Florent Nicart, Jean-Marc Champarnaud, Tibor Csaki, Tamas Gaal, Andre Kempe Abstract 11th International Conference on Implementation and Application of Automata, Taipei, Taiwan, 21-23 August, 2006. Ref. : 2006/011 Overview of Generative and Discriminative hybrid models Guillaume Bouchard Abstract | result.pdf (425.18KB) IDIAP 15 Anniversary Workshop, Martigny, Switzerland, September 12-13, 2006. Ref. : 2006/027 SMART: Research Directions Nicola Cancedda Abstract | iiia06.short.pdf (21.72KB) IIIA - International workshop on Intelligent Information Access, Helsinki, Finland, July 6-8, 2006. Ref. : 2006/016

  
• Year 2005

  A class of rational n-WFSM Auto-Intersections Andre Kempe, Jean-Marc Champarnaud, Jason Eisner, Franck Guingne, Florent Nicart Abstract | ciaa.pdf (183.11KB) CIAA 2005, Sophia-Antipolis, France, June 27-29, 2005. Ref. : 2005/021 A probabilistic interpretation of precision, recall and F-score, with implication for evaluation Cyril Goutte, Eric Gaussier Abstract | xrce_eval.pdf (168.76KB) ECIR 27th European Conference on Information Retrieval,Santiago de Compostela, Spain, 21-23 March, 2005. Ref. : 2004/058 A voice enabled procedure browser for the international space station Manny Rayner, Beth Ann Hockey, Nikos Chatzichrisafis, Kim Farrell, Jean-Michel Renders Abstract | RaynerEAClarissaACL05.pdf (457.08KB) ACL Conference, University of Michigan, 20-25 June, 2005. Ref. : 2005/018 Co-occurence models in music genre classification Peter Ahrendt, Cyril Goutte, Jan Larsen Abstract | co_occurrence_article.pdf (95.08KB) IEEE International workshop on Machine Learning for Signal Processing, Mystic, Connecticut, USA, September 28-30, 2005. Ref. : 2005/031 Contributions à l accès à l information documentaire Eric Gaussier Abstract | publi.pdf (455KB) HDR Report defended at the University Joseph Fourier, Grenoble, France, Dec. 12, 2005 Ref. : 2005/067 German compound analysis with wfsc Anne Schiller Abstract | FSMNLP2005_schiller.pdf (103.15KB) Finite State Methods and Natural Language Processing 2005, Helsinki, 1-2 September 2005. Ref. : 2005/032 Hierarchical Part-Based Visual Object Categorization Guillaume Bouchard, Bill Triggs Abstract Appeared in Computer Vision and Pattern Recognition, Volume 1, pp. 710-715. Ref. : 2005/071 Learning from partially labelled data -- with confidence Eric Gaussier, Cyril Goutte Abstract | xrce_confidence.pdf (912.81KB) Proceedings of Learning with Partially Classified Training Data - ICML 2005 workshop, Bonn, Germany, 7 August, 2005. Ref. : 2005/030 Literality based sample sorting for syntax projection Bruno Cavestro, Nicola Cancedda Abstract | Wclki1005.pdf (114.51KB) Cross-Language knowledge induction workshop, "Babes-Bolyai" University, Cluj-Napoca, Romania, 25 July - 6 August, 2005. Ref. : 2005/039 Relation between PLSA and NMF and implications Eric Gaussier, Cyril Goutte Abstract The 28th annual International ACM SIGIR, Conference on Research and Development in information retrieval, Salvador, Brazil, August 15-19, 2005. Ref. : 2005/029 Traduction automatique statistique avec des segments discontinus Michel Simard, Nicola Cancedda, Bruno Cavestro, Marc Dymetman, Eric Gaussier, Cyril Goutte, Kenji Yamada, Arne Mauser Abstract | final.pdf (143.74KB) Traitement Automatique des Langues Naturelles (TALN 2005), Dourdan,France, 6-10 juin 2005. Ref. : 2005/001 Translating with non contiguous phrase Michel Simard, Nicola Cancedda, Bruno Cavestro, Marc Dymetman, Eric Gaussier, Cyril Goutte, Philippe Langlais, Kenji Yamada, Arne Mauser Abstract | simard05translating.pdf (132.41KB) HLT/EMNLP: Human Language Technology Conference/Conference on Empirical methods in natural language processing, Vancouver, Canada, October 6-8, 2005. Ref. : 2005/042 WFSM Auto-Intersection and join algorithms Andre Kempe, Jean-Marc Champarnaud, Franck Guingne, Florent Nicart Abstract FSMNLP 2005 (5th Int. wrokshop on finite state methods in natural language processing, Helsinki, Finland, September 1-2, 2005. Ref. : 2005/028

  
• Year 2004

  A Geometric view on bilingual lexicon extraction from comparable corpora Eric Gaussier, Jean-Michel Renders, Irina Matveeva, Cyril Goutte, Hervé Dejean Abstract | 2004_013.pdf (94.16KB) 42nd Annual Meeting of the Association for Computational Linguistics, Barcelona, Spain, July 25-26, 2004. Ref. : 2004/013 A note on join and auto-intersection of n-ary rational relations Andre Kempe, Jean-Marc Champarnaud, Jason Eisner Abstract | 2004_045.pdf (305.85KB) Eindhoven FASTAR Days, 2004. Ref. : 2004/045 Algorithms for Weighted multi-Tape Automata Andre Kempe, Franck Guingne, Florent Nicart Abstract | 2004_031.pdf (233.82KB) XRCE Technical Research Report 2004/031. Ref. : 2004/031 Aligning words using matrix factorisation Cyril Goutte, Kenji Yamada, Eric Gaussier Abstract | 2004_015.pdf (88.09KB) 42nd Annual Meeting of the Association for Computational Linguistics, Barcelona, Spain, July 25-26, 2004. Ref. : 2004/015 Assisting medical annotation in Swiss-Prot using statistical classifiers Pavel Dobrokhotov, Cyril Goutte, Anne-Lise Veuthey, Eric Gaussier Abstract | 2004_021.pdf (246.29KB) International Journal of Medical Informatics 74(2-4):317-324. Ref. : 2004/021 Chart-parsing techniques and the prediction of valid editing moves in structured document authoring Marc Dymetman Abstract | 2004_029.pdf (207.22KB) DocEng, ACM Symposium on Document Engineering, Milwaukee, Wisconsin October 28 - 30 2004. Ref. : 2004/029 Computing the follow automaton of an expression Jean-Marc Champarnaud, Florent Nicart, Djelloul Ziadi Abstract Ninth International Conference on Implementation and Application of Automata, Kingston, Canada, July 22-24, 2004. Ref. : 2004/036 Corpus-Based vs. Model-Based Selection of Relevant Features Cyril Goutte, Pavel Dobrokhotov, Eric Gaussier, Anne-Lise Veuthey Abstract | 2004_011.zip (1.9MB) Proceedings of CORIA04, Toulouse, France, March 10-12, 2004, pp. 75-88. Ref. : 2004/011 Generative vs Discriminative approaches to entity Recognition from label deficient data Cyril Goutte, Eric Gaussier, Nicola Cancedda, Hervé Dejean Abstract | 2003_079.pdf (126.99KB) JADT 2004, 7èmes journées internationales analyse statistique des données textuelles, Louvain-la-Neuve, Belgium, 10-12 mars 2004. Ref. : 2003/079 Morphological analysis and generation: a first step in natural language processing Ken Beesley Abstract Fourth international conference on Language Resources and Evaluation, LREC 2004, Lisbon, Portugal, May 26-28 Ref. : 2004/026 NLP Applications based on weighted multi tape automata Andre Kempe Abstract TALN, Fes, Morocco, April 19-22, 2004 Ref. : 2004/002 Reducing Cover Subsequential Transducers Jean-Marc Champarnaud, Franck Guingne, Georges Hansel Abstract Descriptional Complexity of Formal Systems. 6th workshop, London, Ontario, Canada, July 26-28, 2004. Ref. : 2004/037 Similarity relations and cover automata Jean-Marc Champarnaud, Franck Guingne, Georges Hansel Abstract To appear in RAIRO-ITA Ref. : 2004/024 Three new algorithms for WMTAs Andre Kempe, Florent Nicart, Franck Guingne Abstract WATA 2004 Weighted Automata: Theory and Applications, Dresden, June 1-5, 2004. Ref. : 2004/017 Typesetting Deseret Alphabet with LATEX and METAPONT Ken Beesley Abstract The 25th Annual Meeting and Conference of TeX Users Group, Xanthi, Greece, Aug 30-Sept 3 2004. Ref. : 2004/007

  
• Year 2003

  A Probabilistic information retrieval approach to medical annotation in SWISS-PROT Pavel Dobrokhotov, Cyril Goutte, Anne-Lise Veuthey, Eric Gaussier Abstract | dobrokhotov03probabilistic.pdf (82.95KB) Proceedings of Medical informatics Europe (MIE2003), Saint Malo, France, May 4-7, 2003. Ref. : 2003/008 Acyclic Networks maximizing the Printing complexity Franck Guingne, Andre Kempe, Florent Nicart Abstract | Acyclic-Networks.pdf (295.81KB) To appear in the Journal TCS (Theoritical Computer Science) Ref. : 2003/071 Assessing automatically extracted bilingual lexicons for CLIR in vertical Domains Jean-Michel Renders, Hervé Dejean, Eric Gaussier Abstract To appear in \"Lecture Notes in Computer Science\" Ref. : 2003/058 Automatic processing of multilingual medical terminology: applications to thesaurus enrichment and cross-language information retrieval Hervé Dejean, Eric Gaussier, Jean-Michel Renders, Fatia Sadat Abstract | 2003_004.pdf (134.68KB) Artif Intell Med. 2005 Feb;33(2):111-24. PMID: 15811780 [PubMed - indexed for MEDLINE] Ref. : 2003/004 Categorisation de documents PubMed pour l'annotation médicale dans SWISS-PROT Cyril Goutte, Pavel Dobrokhotov, Eric Gaussier, Anne-Lise Veuthey Abstract | goutte_dobrokhotov03.pdf (179.38KB) EGC Conférence, Atelier "Fouille de données et recherche d'informations dans des bases de données multimédia semi-structurées", Lyon, France, January 22, 2003. Ref. : 2003/014 Combining NLP and probabilistic categorisation for document and term selection for SWISS-PROT Medical annotation Pavel Dobrokhotov, Cyril Goutte, Anne-Lise Veuthey, Eric Gaussier Abstract | dobrokhotov03combining.pdf (383.27KB) Proceedings of the 11th International Conference on Intelligent Systems for Molecular Biology (ISMB 2003) Ref. : 2003/009 Creating a web based demo of a finite state morphological analyzer Ken Beesley Abstract Available on http://www.fsmbook.com Ref. : 2003/078 Editing and Authoring: A structural adviser for the XML document authoring Boris Chidlovskii Abstract | p346-chidlovskii.pdf (131.39KB) Pages 203-211 in Proceedings of the 2003 ACM Symposium on Document Engineering, Grenoble, France, November 20-22, 2003. Ref. : 2003/070 Entre syntaxe et sémantique : normalisation de la sortie de l'analyse syntaxique en vue de l'amélioration de l'extraction d'information à partir de textes. Caroline Hagege, Claude Roux Abstract TALN, Batz-sur-Mer,France, 11-14 June 2003. Ref. : 2003/025 MDA-XML : Une expérience de rédaction controlée multilingue basée sur XML Guy Lapalme, Caroline Brun, Marc Dymetman Abstract TALN, Batz-sur-mer, France, 11-14 June 2003. Ref. : 2003/024 Multi-language machine translation through interactive document normalization Aurelien Max Abstract | EACL2003-EAMT-Max.pdf (1008.29KB) EACL Workshop, Budapest, Hungary, 12-17 April 2003. Ref. : 2003/017 Normalization and paraphrasing using symbolic methods Caroline Brun, Caroline Hagege Abstract ACL: Second International workshop on Paraphrasing, Paraphrase Acquisition and Applications, Sapporo, Japan, July 7-12, 2003. Ref. : 2003/044 Problèmes d'intersubjectivité dans l'évaluation des analyseurs syntaxiques Salah Ait-Mokhtar, Caroline Hagege, Agnes Sandor Abstract TALN Conference, Batz-sur-mer, France, June 11-14, 2003. Ref. : 2003/039 Reducing parameter space for word alignment Hervé Dejean, Eric Gaussier, Cyril Goutte, Kenji Yamada Abstract | Dejean.pdf (41.78KB) http://www.cs.unt.edu/~rada/wpt/NAACL/HLT Workshop Building and Using Parallel Texts: Data Driven Machine Translation and Beyond, Edmonton, Canada, May 31, 2003. Ref. : 2003/051 Report on CLEF-2003 experiments: Two Ways of extracting multilingual resources from corpora Hervé Dejean, Eric Gaussier, Jean-Michel Renders, Alexei Vinokourov Abstract | CLEF-2003.pdf (76.36KB) CLEF 2003, Norway, Trondheim, August 21-22, 2003. Ref. : 2003/061 Reversing controlled document authoring to normalize documents Aurelien Max Abstract | EACL2003-SRW-Max.pdf (551.51KB) EACL 11th Conference of the European Chapter of the Association for Computational Linguistics, Budapest, Hungary, April 12-17, 2003. Ref. : 2002/055 Running time complexity of traversing and printing an acyclic automaton Franck Guingne, Andre Kempe, Florent Nicart Abstract CIAA, Santa Barbara, CA, USA, July 16-18,2003. Volume 2759 of Lecture Notes in Computer Science, Springer Verlag, pages 131-140. Ref. : 2003/038 Text Chat in action Jacki O'Neill, David Martin Abstract | Group03_textchatFD2.doc (148KB) Group 2003 Conference, Sanibel Island, Florida, USA, November 9-12, 2003. Ref. : 2003/054 The adequate design of ethnographic outputs for practice: some explorations of the characteristics of design resources Tim Diggins, Peter Tolmie Abstract | Design_Resources_withimages.pdf (417.57KB) 1AD: Frist International Conference on Appliance Design, Bristol, UK May 6-8, 2003. Ref. : 2003/029 Towards interactive text understanding Marc Dymetman, Aurelien Max, Kenji Yamada Abstract ACL 2003, 41st Annual mtg of the association for Computational Linguistics, Sapporo, Japan, July 7-12, 20030. Ref. : 2003/048 Traitement automatique des langues et recherche d'information Eric Gaussier, Christian Jacquemin, Pierre Zweigenbaum Abstract To appear in "Traité Sciences de l'Information - Assistance Intelligente à la recherche d'information" Eds: E.Gaussier et M-H Stefanini Ref. : 2003/042 Virtual operations on virtual networks: the priority union Franck Guingne, Florent Nicart, Jean-Marc Champarnaud, Lauri Karttunen, Tamas Gaal, Andre Kempe Abstract To appear in International Journal of Foundations of computer science Ref. : 2003/010 WFSC - A new weighted finite state compiler Andre Kempe, Christof Baeijs, Tamas Gaal, Franck Guingne, Florent Nicart Abstract 8th Int. Conf. on Implementation and Application of Automata (CIAA 03), Santa Barbara, CA, USA, July 16-18, 2003. volume 2759 of Lecture Notes in Computer Science, Springer Verlag, pages 108-119. Ref. : 2003/037

  
• Year 2002

  A hierarchical model for clustering and categorising documents Eric Gaussier, Cyril Goutte, Kris Popat, Francine Chen Abstract | gaussier02hierarchical.ps.gz (98.94KB) Advances in Information Retrieval -- Proceedings of the 24th BCS-IRSG European Colloquium on IR Research (ECIR-02), Glasgow, March 25-27, 2002. Lecture Notes in Computer Science 2291, pp. 229-247, Springer. Ref. : 2002/004 A rule based Pronoun Resolution System for French François Trouilleux Abstract Proc. of Discourse Anaphora and Anaphor Resolution Colloquium (DAARC 2002), Lisbon, Portugal, Sept. 18-20, 2002. Ref. : 2002/035 Bilingual lexicon extraction: using and enriching multilingual thesauri Hervé Dejean, Eric Gaussier, Fatia Sadat Abstract | HDejean.pdf (101.55KB) Proc. of Terminology Knowledge Extraction, Nancy, France, August 25-30, 2002. Ref. : 2002/029 Bilingual terminology extraction: an approach based on a multilingual thesaurus applicable to comparable corpora Hervé Dejean, Eric Gaussier, Fatia Sadat Abstract | dejean.pdf (77.43KB) Proc. of COLING, Tapei, Taiwan, 24-30 August, 2002. Ref. : 2002/025 Combining labelled and unlabelled data : a case study on Fisher kernels and transductive inference for biological entity recognition Cyril Goutte, Hervé Dejean, Eric Gaussier, Jean-Michel Renders, Nicola Cancedda Abstract | goutte02combining.ps.gz (41.82KB) Proc. of Sixth Conference on Natural Language Learning (CoNLL-2002), Taipei, Taiwan, 24-25 August, 2002. Ref. : 2002/024 Enriching a text by semantic disambiguation for information extraction Bernard Jacquemin, Caroline Brun, Claude Roux Abstract | LREC2002Bernard.pdf (48.89KB) Conference Proceedings LREC, Las Palmas, Spain, June 2, 2002. Ref. : 2002/012 Extraction and recoding of input-Epsilon Cycles in finite state transducers Andre Kempe Abstract volume 313/1 of Theoretical Computer Science, Elsevier Science, pages 145-158. Ref. : 2002/045 Finite State Lazy Operations in NLP Franck Guingne, Florent Nicart Abstract Proc. of CIAA, Tours, France, July 3-5, 2002. Ref. : 2002/040 Insertions et interprétation des expressions pronominales François Trouilleux Abstract | crra-taln02_ftrouilleux.pdf (93.92KB) Proc. of TALN 2002, Nancy, France, 24-27 juin 2002. Ref. : 2002/013 Les outils de TAL au service de la e formation en langues Caroline Brun, Thibault Parmentier, Agnes Sandor, Frederique Segond Abstract in Multilinguisme et Traitement de l Information, Volume dirigé par Frédérique Segond, Hermes, 2002 Ref. : 2002/038 Linguistic Processing of Biomedical Texts Caroline Hagege, Agnes Sandor, Anne Schiller Abstract Proceedings of PorTAL 2002, Portugal for Natural Language processing, Taro, Portugal, June 23-26, 2002. Ref. : 2002/014 Normalisation de Documents par Analyse du Contenu à l''aide d''un modèle Sémantique et d''un Générateur Aurelien Max Abstract Proc. TALN-Recital 2002, Nancy, France, 24-27 juin 2002. Ref. : 2002/023 Probabilistic Models for Hierarchical Clustering and Categorisation : Applications in the information Society Eric Gaussier, Cyril Goutte Abstract | gaussier02probabilistic.ps.gz (50.64KB) Proceedings of the Intl. Conf. on Advances in Infrastructure for Electronic Business, Education, Science and Medicine on the Internet, L'Aquila,Italy, January 21-27 2002. Ref. : 2002/005 Redaction multilingue assistée dans le modele MDA Caroline Brun, Marc Dymetman Abstract To appear in a Book "Multilinguisme et traitement d'information", end of year 2002. Ref. : 2002/052 Word-Sequence Kernels Nicola Cancedda, Eric Gaussier, Cyril Goutte, Jean-Michel Renders Abstract | cancedda03a.pdf (235.79KB) The Journal of Machine Learning Research Ref. : 2002/010

  
• Year 2001

  Language Technologies and patent search and classification David Hull, Salah Ait-Mokhtar, Mathieu Chuat, Andreas Eisele, Eric Gaussier, Greg Grefenstette, Pierre Isabelle, Christer Samuelsson, Frederique Segond Abstract World Patent Information 23 (2001) 265-268 Ref. : 2004/044 Towards a Consistent Logical Framework for Ontological Analysis Aaron Kaplan Abstract Proceedings of the International Conference on Formal Ontology in Information Systems, Ogunquit, Maine, October, 2001. Ref. : 2001/040