Stéphane HUET

Position: Maître de conférences (Lecturer) in computer science
Affiliation: Université d'Avignon (CERI)
Research unit: LIA
Address: 339, chemin des Meinajariès — Agroparc BP 91228 — 84911 AVIGNON Cedex 9 — FRANCE
Phone: +33 4 90 84 35 80
E-mail: stephane(dot)huet[at]univ-avignon(dot)fr

Journals

  1. Julien Bourdaillet, Stéphane Huet, Philippe Langlais and Guy Lapalme. TransSearch: from a Bilingual Concordancer to a Translation Finder. Machine Translation, Volume 24(3-4), pages 241-271, 2010. [link]
  2. Stéphane Huet, Guillaume Gravier and Pascale Sébillot. Morpho-Syntactic Post-Processing of N-Best Lists for Improved French Automatic Speech Recognition. Computer Speech and Language, Volume 24(4), pages 663-684, 2010. [link]

Book chapters

  1. Stéphane Huet and Philippe Langlais. Where Humans Meet Machines: Innovative Solutions to Knotty Natural Language Problems. Amy Neustein and Judith A. Markowitz (eds.). Chapter Translation of Idiomatic Expressions Across Different Languages: A Study of the Effectiveness of TransSearch. pages 185-209, Springer, 2013. [link]
  2. Nathalie Camelin, Boris Detienne, Stéphane Huet, Dominique Quadri and Fabrice Lefèvre. Knowledge Discovery, Knowledge Engineering and Knowledge Management. A. Fred et al. (eds.). Chapter Concept Discovery and Automatic Semantic Annotation for Language Understanding in an Information-Query Dialogue System Using Latent Dirichlet Allocation and Segmental Methods. pages 45-59, Springer, 2013. [link]
  3. Stéphane Huet, Gwénolé Lecorvé, Guillaume Gravier and Pascale Sébillot. Multimodal Processing and Interaction: Audio, Video, Text. Petros Maragos, Alexandros Potamianos, Patrick Gros (eds.). Chapter Toward the Integration of Natural Language Processing and Automatic Speech Recognition: Using Morpho-syntax and Pragmatics for Transcription. pages 201-218, Springer, 2008. [link]

International conferences

  1. Raphaël Rubino, Stéphane Huet, Fabrice Lefèvre and Georges Linarès. Statistical Post-Editing of Machine Translation for Domain Adaptation. Proceedings of the 16th Annual Conference of the European Association for Machine Translation (EAMT), pages 221-228, Trento, Italy, May 2012. [article]
  2. Nathalie Camelin, Boris Detienne, Stéphane Huet, Dominique Quadri and Fabrice Lefèvre. Concept Discovery for Language Understanding in an Information-Query Dialogue System. Proceedings of the International Conference on Knowledge Discovery and Information Retrieval (KDIR), Paris, France, October 2011. [article]
  3. Floran Boudin, Stéphane Huet and Juan-Manuel Torres-Moreno. A Graph-based Approach to Cross-language Multi-document Summarization. Proceedings of the 12th International Conference on Intelligent Text Processing and Computational Linguistics (CICLing), Research journal on Computer science and computer engineering with applications (Polibits), Volume 43, pages 113-118, Poster session, Tokyo, Japan, February 2011. [article]
  4. Stéphane Huet, Julien Bourdaillet, Philippe Langlais and Guy Lapalme. Harnessing the Redundant Results of Translation Spotting. Proceedings of the 12th Machine Translation Summit (MT Summit), Ottawa, Canada, August 2009. [article] [poster]
  5. Stéphane Huet, Julien Bourdaillet and Philippe Langlais. TS3: an Improved Version of the Bilingual Concordancer TransSearch. Proceedings of the 13th Annual Conference of the European Association for Machine Translation (EAMT), pages 20-27, Barcelona, Spain, May 2009. [article] [slides]
  6. Stéphane Huet, Guillaume Gravier and Pascale Sébillot. Morphosyntactic Resources for Automatic Speech Recognition. Proceedings of the 6th International Conference on Language Resources and Evaluation (LREC), pages 692-698, Marrakech, Morocco, May 2008. [article] [poster]
  7. Stéphane Huet, Guillaume Gravier and Pascale Sébillot. Morphosyntactic Processing of N-Best Lists for Improved Recognition and Confidence Measure Computation. Proceedings of the 8th Annual Conference of the International Speech Communication Association (Interspeech), pages 1741-1744, Antwerp, Belgium, August 2007. [article]
  8. Stéphane Huet, Guillaume Gravier and Pascale Sébillot. Are Morphosyntactic Taggers Suitable to Improve Automatic Transcription?. Proceedings of the 9th International Conference on Text, Speech and Dialogue (TSD), Lecture Notes in Computer Science, Volume 4188/2006, pages 391-398, Brno, Czech Republic, September 2006. [link] [article] [slides]

Peer reviewed international workshops

  1. Mohamed Morchid, Stéphane Huet and Richard Dufour. A Topic-based Approach for Post-processing Correction of Automatic Translations. Proceedings of the 11th International Workshop on Spoken Language Translation (IWSLT), Lake Tahoe, CA, USA, December 2014. [article]
  2. Stéphane Huet, Elena Manishina and Fabrice Lefèvre. Factored Machine Translation Systems for Russian-English. Proceedings of the ACL 8th Workshop on Statistical Machine Translation (WMT), Sofia, Bulgaria, August 2013. [article]
  3. Stéphane Huet and Philippe Langlais. Identifying the Translations of Idiomatic Expressions using TransSearch. Proceedings of the 8th International Workshop on Natural Language Processing and Cognitive Science (NLPCS), pages 45-56, Copenhagen, Denmark, August 2011. [article] [slides]
  4. Stéphane Huet and Fabrice Lefèvre. Unsupervised Alignment for Segmental-based Language Understanding. Proceedings of the EMNLP Workshop on Unsupervised Learning in NLP (UNSUP), pages 97-104, Edinburgh, UK, July 2011. [article] [poster]
  5. Nathalie Camelin, Boris Detienne, Stéphane Huet, Dominique Quadri and Fabrice Lefèvre. Unsupervised Concept Annotation using Latent Dirichlet Allocation and Segmental Methods. Proceedings of the EMNLP Workshop on Unsupervised Learning in NLP (UNSUP), pages 72-81, Edinburgh, UK, July 2011. [article] [poster]
  6. Marion Potet, Raphaël Rubino, Benjamin Lecouteux, Stéphane Huet, Laurent Besacier, Hervé Blanchon and Fabrice Lefèvre. The LIGA (LIG/LIA) Machine Translation System for WMT 2011. Proceedings of the EMNLP 6th Workshop on Statistical Machine Translation (WMT), pages 440-446, Edinburgh, UK, July 2011. [article]
  7. Stéphane Huet, Julien Bourdaillet, Alexandre Patry and Philippe Langlais. The RALI Machine Translation System for WMT 2010. Proceedings of the ACL Joint 5th Workshop on Statistical Machine Translation and Metrics (WMT), pages 103-109, Uppsala, Sweden, July 2010. [article] [poster]

National and French-speaking conferences

  1. Raphaël Rubino, Stéphane Huet, Fabrice Lefèvre and Georges Linarès. Post-édition statistique pour l’adaptation aux domaines de spécialité en traduction automatique. Actes de la 19ème conférence sur le Traitement Automatique des Langues Naturelles (TALN), short paper, pages 527-534, Grenoble, France, June 2012. [article]
  2. Stéphane Huet, Florian Boudin and Juan-Manuel Torres-Moreno. Utilisation d'un score de qualité de traduction pour le résumé multi-document cross-lingue. Actes de la 18ème conférence sur le Traitement Automatique des Langues Naturelles (TALN), Montpellier, France, June 2011. [article]
  3. Stéphane Huet and Fabrice Lefèvre. Alignement automatique pour la compréhension littérale de l'oral par approche segmentale. Actes de la 18ème conférence sur le Traitement Automatique des Langues Naturelles (TALN), short paper, Montpellier, France, June 2011. [article]
  4. Julien Bourdaillet, Stéphane Huet and Philippe Langlais. Alignement de traductions rares à l'aide de paires de phrases non alignées. Actes de la 17ème conférence sur le Traitement Automatique des Langues Naturelles (TALN), Montreal, Canada, July 2010. [article]
  5. Stéphane Huet, Julien Bourdaillet and Philippe Langlais. Intégration de l'alignement de mots dans le concordancier bilingue TransSearch. Actes de la 16ème conférence sur le Traitement Automatique des Langues Naturelles (TALN), Senlis, France, June 2009. [article]
  6. Julien Bourdaillet, Stéphane Huet, Fabrizio Gotti, Guy Lapalme and Philippe Langlais. Enhancing the Bilingual Concordancer TransSearch with Word-level Alignment. Proceedings of the 22nd Conference of the Canadian Society for Computational Studies of Intelligence (Canadian AI), Lecture Notes in Computer Science, Volume 5549/2009, pages 27-38, Kelowna, Canada, May 2009. [link] [article] [poster]
  7. Stéphane Huet, Guillaume Gravier and Pascale Sébillot. Un modèle multi-sources pour la segmentation en sujets de journaux radiophoniques. Actes de la 15ème conférence sur le Traitement Automatique des Langues Naturelles (TALN), pages 49-58, Avignon, France, June 2008. [article]
  8. Stéphane Huet, Guillaume Gravier and Pascale Sébillot. Peut-on utiliser les étiqueteurs morphosyntaxiques pour améliorer la transcription automatique ?. Actes des 26èmes journées d'étude sur la parole (JEP), pages 317-320, Dinard, France, June 2006. [article] [poster]
  9. Stéphane Huet. Classification de signaux myoélectriques. Actes de la 3ème conférence pour l'essor des technologies d'assistance (Handicap 2004), Paris, France, June 2004. [article]

Other publications

  1. Luis Adrián Cabrera-Diego, Stéphane Huet, Bassam Jabaian, Alejandro Molina, Juan-Manuel Torres-Moreno, Marc El-Bèze and Barthélémy Durette. Algorithmes de classification et d'optimisation : participation du LIA/ADOC à DEFT'14. Actes de la 10ème édition du défi fouille de textes (DEFT), Marseille, France, July 2014. [article]
  2. Julien Bourdaillet, Fabrizio Gotti, Stéphane Huet, Philippe Langlais and Guy Lapalme. TransSearch : un moteur de recherche de traductions. Actes de la 17ème conférence sur le Traitement Automatique des Langues Naturelles (TALN), demo session, Montreal, Canada, July 2010. [article]
  3. Stéphane Huet, Pascale Sébillot and Guillaume Gravier. Introduction de connaissances linguistiques en reconnaissance de la parole : un état de l'art. Rapport de Recherche IRISA, No1804, May 2006. [report]

Current projects

MaRDi (2012-2015). Man-robot dialogue. Participants: Supélec, LIA, LAAS and Acapela Group. Project leader: Olivier Pietquin. Funding: ANR.

Previous projects

OptimNLP (2011-2012). Use of combinatorial optimization in machine translation. Participant: LIA. Project leader: Fabrice Lefèvre. Funding: LIA.

PORT-MEDIA (2009-2012). Robustness and multilingual multidomain portability of spoken language understanding systems. Participants: LIA, LIG, LIUM, LORIA and ELDA. Project leader: Fabrice Lefèvre. Funding : ANR.

TransSearch 3 (2007-2010). Overhauling of the bilingual concordancer TransSearch, used by professional translators to consult large databases of past translations. Participants: RALI and Terminotix. Project leaders: Philippe Langlais and Guy Lapalme. Funding: NSERC.

Demi-ton (2005-2008). Multimodal description for the automatic structuration for television broadcasts. Participants: IRISA and INA. Project leader: Patrick Gros. Funding: Action concertée incitative.

Currently

Université d'Avignon

Previously

Université d'Avignon

Université de Rennes 1

INSA de Rennes