Thomas Lavergne

LIMSI-CNRS
BP 133
F-91403 Orsay Cedex (France)

E-mail: thomas.lavergne@limsi.fr
Phone:+33 (0)1 69 85 80 41

I am a researcher at LIMSI/CNRS in the Spoken Language Processing Group. My main research topics are machine learning and its application to statistical machine translation.

I'm currently working on machine translation using discriminative learning technics, in particular using conditional random fields. I'm also working on very large scale CRFs and the main author of Wapiti.

Publications

Journals

• Designing an improved discriminative word aligner
N. Tomeh, T. Lavergne, A. Allauzen, F. Yvon, In the International Journal of Computational Linguistics and Applications (IJCLA), 2011
[pdf] [bib]
• Efficient learning of sparse conditional random fields for supervised sequence labelling
N. Sokolovska, T. Lavergne, O. Cappé, F. Yvon, In IEEE - Journal of Selected Topics in Signal Processing (STSP), 2010
[pdf] [bib] [lnk]
• Filtering artificial texts with statistical machine learning techniques
T. Lavergne, T. Urvoy, F. Yvon, In Language Resources and Evaluation (LRE), special issue on Plagiarism and Authorship Analysis, 2010
[pdf] [bib] [lnk]
• Tracking web spam with html style similarities
T. Urvoy, E. Chauveau, P. Filoche, T. Lavergne, In ACM Transactions on the Web (TWEB), vol. 2, No. 1, February 2008
[pdf] [bib] [lnk]

International conferences

• limsi @ wmt12
H. Le, T. Lavergne, A. Allauzen, M. Apidianaki, L. Gong, A. Max, A. Sokolov, G. Wisniewski, F. Yvon, In Proceedings of the 6th Workshop on Statistical Machine Translation (WMT), 2011
• Joint Segmentation and pos Tagging for Arabic Using a crf-based Classifier
S. Gahbiche-Braham, H. Bonneau-Maynard, T. Lavergne, F. Yvon, In Proceedings of The International Conference on Language Resources and Evaluation (LREC), 2012
[pdf]
• limsi's experiments in domain adaptation for iwslt11
T. Lavergne, A. Allauzen, H. Le, F. Yvon, In Proceedings of the International Workshop on Spoken Language Translation (IWSLT), 2011
[pdf]
• Advances on Spoken Language Translation in the Quaero Program
K. Boudahmane, B. Buschbeck, E. Cho, J. M. Crego, M. Freitag, T. Lavergne, H. Ney, J. Niehues, S. Peitz, J. Senellart, A. Sokolov, A. Waibel, T. Wandmacher, J. Wübker, F. Yvon In Proceedings of the International Workshop on Spoken Language Translation (IWSLT), 2011 Invited talk
[pdf]
• From n-gram-based to crf-based translation models
T. Lavergne, A. Allauzen, F. Yvon, J. M. Crego, In Proceedings of the 6th Workshop on Statistical Machine Translation (WMT), 2011
[pdf] [bib] [lnk]
• limsi @ wmt11
A. Allauzen, H. Bonneau-Maynard, H. Le, A. Max, G. Wisniewski, F. Yvon, G. Adda, J. Crego, A. Lardilleux, T. Lavergne, A. Sokolov In Proceedings of the 6th Workshop on Statistical Machine Translation (WMT), 2011
[pdf] [bib] [lnk]
• Practical very large scale crfs
T. Lavergne, O. Cappé, F. Yvon, In Proceedings of the Conference of the 48th Annual Meeting of the Association for Computational Linguistic (ACL), 2010
[pdf] [bib] [lnk]
• Transformation rules and monte-carlo sampling: a different approach for statistical paraphrase generation
J. Chevelu, T. Lavergne, Y. Lepage, T. Moudenc, In Proceedings of the 10th Conference of the Pacific Association for Computational Linguistics (PACLING), 2009
[pdf] [bib]
• Introduction of a new paraphrase generation tool based on monte-carlo sampling
J. Chevelu, T. Lavergne, Y. Lepage, T. Moudenc, In Proceedings of the Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and the 4th International Joint Conference on Natural Language Processing (ACL-IJCNLP), 2009
[pdf] [bib] [lnk]
• Detecting fake content with relative entropy scoring
T. Lavergne, T. Urvoy, F. Yvon, In Proceedings of International Workshop on Plagiarism Analysis, Authorship Identification, and Near-Duplicate Detection (PAN), 2008
[pdf] [bib] [lnk]
• Taxonomie de textes peu-naturels
T. Lavergne, In Proceedings of 9th International Conference on Textual Data statistical Analysis (JADT), 2008
[pdf] [bib] [lnk]
• Tracking web spam with hidden style similarity
T. Urvoy, T. Lavergne, P. Filoche, In International Workshop on Adversarial Information Retrieval on the Web (AIRWeb), 2006
[pdf] [bib] [lnk]

National conferences

• Repérage des entités nommées pour l'arabe : adaptation non-supervisée et combinaison de systèmes
S. Gahbiche-Braham, H. Bonneau-Maynard, T. Lavergne and F. Yvon, In Traitement Automatique des Langues Naturelles (TALN), 2012
• Unnatural language detection
T. Lavergne, In Proceedings of RJCRI'06: Young Scientists' conference on Information Retrieval
[pdf] [bib] [lnk]

Others

• Détection des textes non-naturels
T. Lavergne, Phd Thesis, ENST Paris & Orange Labs, 2009
[pdf] [bib]
• Prédicats algébriques d'entiers
T. Lavergne, Master Thesis, Université de Rennes 1 & Galion - IRISA, 2005
[pdf]

Research interests