Accueil > Sites personnels > Thierry Poibeau

Thierry Poibeau

Directeur de recherche at CNRS ; Head of the Lattice laboratory

par Thierry POIBEAU - publié le

Since 2012, I am the head of the CNRS Lattice laboratory.

I am a CNRS researcher (CNRS is the French Institute for Fundamental Research), working at LaTTiCe (Langues, Textes, Traitements informatiques et Cognition). Since 2007, I am also an Affiliated Lecturer at the Department of Theoretical and Applied Linguistics (DTAL) of the University of Cambridge. During the academic year 2008-2009, I was a Visiting Research Fellow at Corpus Christi College.

From 2003 to 2009, I worked at Laboratoire d’Informatique de Paris-Nord. In 2002-2003, I was an associate professor at the Centre de Recherche en Ingénierie Multilingue (CRIM) within the Institut National des Langues et Civilisations Orientales (INaLCO) and before that a researcher at Thales Recherche et Technologie (1998-2002).

I mainly work on Natural Language Processing (NLP), especially on the following topics : Information Extraction, Question Answering, Semantic Zoning, Knowledge Acquisition from text and Named Entity tagging. Apart from NLP, my main interests include Language Acquisition, Cognitive Science, Epistemology and the History of Linguistics.

Recent publications

2013

- Tim Van de Cruys, Thierry Poibeau and Anna Korhonen (2013). A Tensor-based Factorization Model of Semantic Compositionality. In Proceedings of the NAACL-HLT 2013, Atlanta, US.

- Elisa Omodei, Jean-Philippe Cointet and Thierry Poibeau (2013). The Socio-Epistemic Dynamics of Scientific Research. Proc. European Conf. on Complex Systems, Barcelona.

- Elisa Omodei, Jean-Philippe Cointet and Thierry Poibeau (2013). A symmetric approach to understand the dynamics of scientific collaborations and knowledge production. Proc. Conf. conférence sur les modèles et l’analyse des réseaux : Approches mathématiques et informatiques, Saint-Etienne.

- Aline Villavicencio, Thierry Poibeau, Anna Korhonen and Afra Alishahi (2013). Cognitive Aspects of Computational Language Acquisition. Springer (Theory and Applications of Natural Language Processing). 316 p. 60 illus. ISBN 978−3−642−31862−7.

- Thierry Poibeau, Aline Villavicencio, Anna Korhonen and Afra Alishahi (2012). Computational Modeling as a Methodology for Studying Human Language Learning . In Cognitive Aspects of Computational Language Acquisition. Springer (Theory and Applications of Natural Language Processing).

- Thierry Poibeau, Aline Villavicencio (2013). Workshop "Language, Cognition and Computational Models", Ecole normale supérieure. Proceedings under preparation.

2012

- Elisa Omodei, Thierry Poibeau and Jean-Philippe Cointet (2012). "Multi-Level Modeling of Quotation Families Morphogenesis", Proceedings of the 2012 ASE/IEEE International Conference on Social Computing, Amsterdam, 2012

- Tim Van de Cruys, Laura Rimell, Thierry Poibeau, and Anna Korhonen (2012). Multi-way Tensor Factorization for Unsupervised Lexical Acquisition. In Proceedings of the 24th International Conference on Computational Linguistics (COLING), Mumbai, India.

- Pierre Marchal, Thierry Poibeau and Yves Lepage (2012). "Representing the Continuum between Arguments and Adjuncts within Predicate-Frames”. NINJAL International Symposium on “Valency Classes and Alternations in Japanese”, Tokyo, August 2012.

- Thierry Poibeau, Horacio Saggion, Jakub Piskorski and Roman Yangarber (2012). Multi-source, Multilingual Information Extraction and Summarization. Springer-Verlag, Theory and Applications of Natural Language Processing, Berlin & Heidelberg. XXIV + 316 p., 55 illus. ISBN 978−3−642−28568−4.

- Horacio Saggion and Thierry Poibeau (2012). "Automatic Text Summarization : A Short Introduction". In Multi-source, Multilingual Information Extraction and Summarization (Poibeau et al., ed). Springer-Verlag, Theory and Applications of Natural Language Processing, Berlin & Heidelberg.

- Gilles Col, Jeanne Aptekman, Stéphanie Girault, and Thierry Poibeau (2012). "Gestalt Compositionality and Instruction-Based Meaning Construction". Cognitive Processing, Springer, Vol. 13, Issue 2, pp. 151-170. ISSN 1612-4782 (Print) & 1612-4790 (online).

- Robert Berwick, Anna Korhonen, Thierry Poibeau and Aline Villavicencio (2012). Proceedings of the EACL Workshop on Computational Models
of Language Acquisition and Loss. European Chapter of the Association for Computational linguistics.

- Frederic Landragin, Thierry Poibeau and Bernard Victorri (2012). ANALEC : a New Tool for the Dynamic Annotation of Textual Data. Proceedings of the Eigth International Conference on Language Resources and Evaluation (LREC’12), Istanbul, ISBN 978-2-9517408-7-7.

- Laura Rimell, Thierry Poibeau and Anna Korhonen (2012). Merging Lexicons for Higher Precision Subcategorization Frame Acquisition. Proceedings of the LREC 2012 Workshop on Language Resource Merging, Istanbul.

2011

- Yufan Guo, Anna Korhonen and Thierry Poibeau (2011). "A Weakly-supervised Approach to Argumentative Zoning of Scientific Documents". Proceedings of Empirical Methods in Narural Language Processing (EMNLP). Edinburgh.

- Tim van de Cruys, Thierry Poibeau and Anna Korhonen (2011). "Latent Vector Weighting for Word Meaning in Context ". Proceedings of Empirical Methods in Narural Language Processing (EMNLP). Edinburgh.

- Thierry Poibeau (2011). Traitement automatique du contenu textuel. Lavoisier, Paris, ISBN 978-2-7462-3191-7. 230 pages.

- Michel Généreux, Thierry Poibeau and Moshe Koppel (2011). "Sentiment analysis using automatically labelled financial news". In Affective Computing and Sentiment Analysis : Metaphor, Ontology, Affect and Terminology (Khurshid Ahmad, ed.). Springer., Series : Text, Speech and Language Technology, Vol. 45. ISBN 978-94-007-1756-5. pp. 111-126.

- Mani Ezzat and Thierry Poibeau (2011). "A New framework for Annotating Semantic Relations in Corpora". Proceedings of Recent Advances in Natural Language Processing (RANLP). Hissar (Bulgaria).

- Thierry Poibeau (2011). "Controversies and Misunderstandings about Meaning On the reception of Odgen and Richards’ book, The Meaning of Meaning". Nodus Publikationen, to be published (extended version of my ICHoLS XI publication).

2010

- Barry Devereux, Nicholas Pilkington, Thierry Poibeau and Anna Korhonen (2010). "Towards unrestricted, large-scale acquisition of feature-based conceptual representations from corpus data". Research on Language and Computation 7(2-4). pp. 137-170.

- Cédric Messiant, Kata Gábor, et Thierry Poibeau (2010). « Acquisition de connaissances lexicales à partir de corpus : la sous-catégorisation verbale en français ». Traitement Automatique des Langues, 51/1, 2010.

- Aurélien Bossard, Michel Généreux, et Thierry Poibeau (2010). « Résumé automatique de textes d’opinion ». Traitement Automatique des Langues, 51/3, pp. 47-73.

- Cédric Messiant et Thierry Poibeau (2010). "Automatic Lexical Acquisition from Corpora, some Limitations and some Tentative Solutions". Cahiers du Cental (special issue on eLexicography in the 21st Century : New Challenges, New Applications), Presses Universitaires de Louvain, 2010.

- Lin Sun, Thierry Poibeau, Anna Korhonen and Cedric Messiant (2010). "Investigating the cross-linguistic potential of VerbNet-style classification". Proceedings of COLING. Beijing, China.

- Barry Devereux, Nicholas Pilkington, Thierry Poibeau and Anna Korhonen (2010). "Large-Scale Acquisition of Feature-Based Conceptual Representations from Textual Corpora". Proceedings of the Annual Meeting of the Cognitive Science Society, Portland.

- Barry Devereux, Nicholas Pilkington, Thierry Poibeau and Anna Korhonen (2010). "The Acquisition of Unconstrained Feature-Based Conceptual Representations from Corpora". Proceedings of the Workshop on Concepts, Actions, and Objects : Functional and Neural Perspective, Rovereto, Italie.

2009

- Thierry Poibeau et Dominique Dutoit (2009). “Automatic extraction of paraphrastic phrases from small size corpora”. In Linguisticae Investigationes. John Benjamins. Amsterdam. Vol. 32 n°1. ISSN 0378-4169. pp. 77–98 (hal-00436303).

- Thierry Poibeau (2009). “Boosting the Robustness of a Named Entity Recognizer”. International Journal of Semantic Computing. World Scientific. Vol. 3, n°1. ISSN : 1793-351X. pp. 91–104 (hal-00436301).

- Thierry Poibeau (2011). Traitement automatique du contenu textuel. Rapport interne.

- Adeline Nazarenko, Thierry Poibeau et Laurent Audibert (2009). Actes de la conférence Traitement Automatique des Langues Naturelles. Association pour le Traitement Automatique des Langues (ATALA). Senlis, France. 550 pages (hal-00436263).

- Afra Alishahi, Thierry Poibeau et Aline Villavicencio (2009). Proceedings of the second Cognitive Aspects of Computational Language Learning Workshop. Association for Computational Linguistics. Athènes, Grèce. 90 pages (hal-00437371).

- Aurélien Bossard et Thierry Poibeau (2009) “Integrating Document Structure into a Multi-Document Summarizer”. Proceedings of Recent Advances in Natural Language Processing (RANLP 2009). Borovets. Poster (hal-00437982).

- Aurélien Bossard, Michel Généreux et Thierry Poibeau (2009) “CBSEAS, a Summarization System - Integration of Opinion Mining Techniques to Summarize Blogs”. Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2009), Demonstrations Session, Grèce (hal-00397036).

- Amanda Bouffier et Thierry Poibeau (2009). “Analyzing the Scope of Conditions in Texts : A Discourse-Based Approach”. Proceedings of the 11th Conference of the Pacific Association for Computational Linguistics (PACLING 2009), Sapporo (hal-00436258).

- Erwan Moreau, Isabelle Tellier, Antonio Balvet, Grégoire Laurence, Antoine Rozenknop et Thierry Poibeau (2009). « Annotation fonctionnelle de corpus arboré avec des Champs Aléatoires Conditionnels ». Actes de la conférence Traitement Automatique des Langues Naturelles (TALN 2009), Senlis, France (hal-00436330).

teaching and lecturing

Regularly lecturing in various institutions
- Information extraction, at INALCO
- Computational and corpus linguistics at the University of Cambridge

See also the "manuscrit linguistique cognition" group at Ecole normale supérieure.

Recent projects

- European project FP7 STREP PANACEA (with the University of Cambridge)
- Projet BlogSem (Complex Systems National Network) : automatic analysis of topical dynamics online

PhD students

ongoing

- Miquel Cornudella Gaya (2014-, Cifre grant with Sony CSL Paris) : modeling language evolution
- Zorana Ratkovic (2010- ; project funded) : parsing for information extraction from texts
- Pierre Marchal (2010- ; national PhD grant) : lexical acquisition for Japanese

past PhD students

- Mani Ezzat (2009-2013 ; Cifre grant with Arisem) : automatic acquisition of relations between entities (now working as a research engineer at Exalead)
- Yufan Guo (2009-2013, co-supervision with Anna Korhonen ; funded by Cambridge) : text zoning of scientific texts
- Cédric Messiant (2006-2010 ; national DGA grant) : automatic lexical acquisition from large corpora (now working as a research engineer at Ecreall, a start-up in Lille)
- Aurélien Bossard (2006-2010 ; national PhD grant) : automatic summarization (now an associate professor at Université Paris 8)
- Amanda Bouffier (2004—2008 ; national PhD grant) : discursive analysis of medical texts (now an independent consultant in text mining)

Voir en ligne : http://hal.archives-ouvertes.fr/ind...