Marc Dymetman

Phone : +33 (0)4 76 61 50 66
Fax : +33 (0)4 76 61 50 99
marc.dymetman@xrce.xerox.com


I am a Principal Scientist in the Machine Learning for Document Access and Translation area.

Research Interests

Currently:

  • Statistical Machine Translation
  • Machine Learning for NLP applications

Previously:

  • Multilingual Document Authoring and Generation
  • Unification and Logic Grammars for Machine Translation (Reversible Grammars)
  • Formal models of Parsing and Generation (Group Theory and Computational Linguistics;Generalized Greibach Normal Form for DCGs)
  • Paper-Digital Interfaces (Intelligent Paper)

Education

1992 Doctorat d'État en Informatique and Habilitation à Diriger des Recherches (HDR), Université Joseph Fourier, Grenoble: Transformations de Grammaires Logiques et Réversibilité en Traduction Automatique

1977 Agrégation de Mathématiques, Université Paris 6

1976 DEA de Mathématiques, Université Paris 6: Courbes Elliptiques et Nombres Transcendants

1975 Maîtrise de Mathématiques, Université Paris 6

Professional History

1994-present Principal Scientist (since 2001). Currently in the Cross-Language Technologies area. Research areas: Statistical Machine Translation, Multilingual Generation and Authoring, Computational Linguistics, Paper-Digital interfaces.

1986-1994 Researcher, Federal Government of Canada, CITI (previously CWARC), Montreal, Canadian Department of Industry and Science (previously Department of Communications). Research areas: Machine Translation, Reversibility of Parsing and generation in NLP, Transformations of Unification Grammars and Logic Programs.

1985-1986 Researcher, GETA (Groupe d’Études pour la Traduction Automatique, Grenoble), Grenoble. Research area: Machine Translation.

1983-1984 International Fellow, SRI International, Artificial Intelligence Center. Research area: NLP and Commonsense Reasoning.

1981-1983 Researcher, GETA (Groupe d’Études pour la Traduction Automatique, Grenoble). Research area: Machine Translation.

1978-1980 Researcher, DGRST (Délégation générale de la recherche scientifique et technique), Grenoble. Research Focus : Visual Object Recognition, Maximum Entropy for Probabilistic Graphs.

1977-1978 Professeur Agrégé de mathématiques at Lycée Champollion, Grenoble.

Publications

  • Benjamin Roth, Andrew McCallum, Marc Dymetman and Nicola Cancedda. Machine Translation Using Overlapping Alignments and SampleRank. In Proc. AMTA 2010.
  • Marc Dymetman, Nicola Cancedda. Intersecting Hierarchical and Phrase-Based Models of Translation. Formal Aspects and Algorithms. In Proc. SSST-4, August 2010. http://www.aclweb.org/anthology/W/W10/W10-3801.pdf
  • Lucia Specia, Nicola Cancedda, Marc Dymetman. A Dataset for Assessing Machine Translation Evaluation Metrics. In LREC 2010. www.lrec-conf.org/proceedings/lrec2010/pdf/504_Paper.pdf
  • Wilker Aziz, Marc Dymetman, Shachar Mirkin, Lucia Specia, Nicola Cancedda, Ido Dagan. Learning an Expert from Human Annotations in Statistical Machine Translation: the Case of Out-of-Vocabulary Words. In EAMT 2010. http://www.mt-archive.info/EAMT-2010-Aziz.pdf
  • Mikhail Zaslavskiy; Marc Dymetman; Nicola Cancedda. Phrase-Based Statistical Machine Translation as a Traveling Salesman Problem. In ACL 2009. www.aclweb.org/anthology/P/P09/P09-1038.pdf
  • Shachar Mirkin; Lucia Specia; Nicola Cancedda; Ido Dagan; Marc Dymetman; Idan Szpektor. Source-Language Entailment Modeling for Translating Unknown Terms. In ACL 2009.
  • Lucia Specia, Marco Turchi, Nicola Cancedda, Marc Dymetman and Nello Cristianini. Estimating the Sentence-Level Quality of Machine Translation Systems. In EAMT 2009.
  • Nadi Tomeh, Nicola Cancedda, Marc Dymetman. Complexity Based Phrase-Table Filtering for Statistical Machine Translation. MT Summit 2009 (Machine Translation Summit XII), Ottawa, Ontario, Canada, August 26-30, 2009.
  • C. Goutte, N. Cancedda, M. Dymetman and G. Foster (Editors). Learning Machine Translation. MIT Press 2009.
  • N. Cancedda, M. Dymetman, G. Foster and C. Goutte. A Statistical Machine Translation Primer. In Learning Machine Translation, MIT Press 2009.
  • Vassilina Nikoulina and Marc Dymetman. Experiments in Discriminating Phrase-Based Translations on the Basis of Syntactic Coupling Features. Second Workshop on Syntax and Structure in Statistical Translation (SSST-2), 2008
  • Vassilina Nikoulina and Marc Dymetman. Using Syntactic Coupling Features for Discriminating Phrase-Based Translations (WMT-08 Shared Translation Task). In third Workshop on Statistical Machine Translation, 2008
  • Ergun Biçici, Marc Dymetman. Dynamic Translation Memory: Using Statistical Machine Translation to Improve Translation Memory Fuzzy Matches. CICLing 2008: 454-465
  • Nicola Cancedda, Marc Dymetman, Éric Gaussier, Cyril Goutte. An Elastic-Phrase Model for Statistical Machine Translation. In Jounées de l'ATALA (Assocation pour le Traitement Automatique des Langues), Paris, 2007.
  • Michel Simard, Nicola Cancedda, Bruno Cavestro, Marc Dymetman, Éric Gaussier, Cyril Goutte, Kenji Yamada, Philippe Langlais, Arne Mauser. Translating with non-contiguous Phrases. HLT/EMNLP 2005
  • Marc Dymetman. Chart-parsing techniques and the prediction of valid editing moves in structured document authoring. ACM Symposium on Document Engineering 2004: 229-238
  • Caroline Brun, Marc Dymetman, Eric Fanchon, Stanislas Lhomme, Sylvain Pogodalla. Semantically-based text authoring and the concurrent documentation of experimental protocols. ACM Symposium on Document Engineering 2003: 193-202
  • Dymetman, Marc, Max, Aurélien, Yamada, Kenji. Towards Interactive Text Understanding (ACL – Short Papers, 2003)
  • Caroline Brun, Marc Dymetman, Eric Fanchon, Stanislas Lhomme. Controlled Authoring of Biological Experiment Reports. EACL 2003: 195-198
  • Marc Dymetman. Text Authoring, Knowledge Acquisition and Description Logics. COLING 2002
  • Marc Dymetman. Document Content Authoring and Hybrid Knowledge Bases. KRDB 2002
  • Marc Dymetman and Frédéric Tendeau. Context-Free Grammar Rewriting and the Transfer of Packed Linguistic Structures. In Proceedings COLING 2000, Saarbrücken, August.
  • Marc Dymetman, Veronika Lux and Aarne Ranta. XML and Multilingual Document Authoring: Convergent Trends. In Proceedings COLING 2000, Saarbrücken, August.
  • Caroline Brun, Marc Dymetman and Veronika Lux. Document Structure and Multilingual Authoring. First International Conference on Natural Language Generation, INLG 2000, Mitzpe Ramon, Israel, June.
  • Marc Dymetman. Some Remarks on the Geometry of Grammar. In Proceedings of MOL'6 (6th Meeting on the Mathematics of Language), Orlando, FA, July 1999.
  • Marc Dymetman. Group Theory and Computational Linguistics. In Journal of Logic, Language and Information (JOLLI), Volume 7, No. 4, 1998.
  • Marc Dymetman. Group Theory and Linguistic Description. In Proceedings COLING 98, Montreal, August.
  • Marc Dymetman and Max Copperman. Intelligent Paper. In Roger D. Hersh, Jacques André, and Heather Brown, editors, Electronic Publishing, Artistic Imaging, and Digital Typography, volume 1375 of Lecture Notes in Computer Science, pages 392-405. Springer, 1998. 7th International Conference on Electronic Publishing, EP'98. (Invited Keynote Paper).
  • Patrick Blackburn, Marc Dymetman, Alain Lecomte, Aarne Ranta, Christian Retoré, and Eric Villemonte de la Clergerie. Logical Aspects of Computational Linguistics: an Introduction. In Christian Rétoré, editor, Logical Aspects of Computational Linguistics, volume 1328 of LNCS/LNAI, pages 1-20. Springer, 1997. (LACL'96, Nancy).
  • Marc Dymetman. Interaction-free grammars, Chart-parsing, and the Compact Representation of Ambiguity. In Proceedings IJCAI, Nagoya, Japan, August 1997.
  • Marc Dymetman and Max Copperman. Extended dependency structures and their formal interpretation. In Proceedings COLING 96, Copenhagen, August 1996.
  • Marc Dymetman, Julie Brousseau, George Foster, Pierre Isabelle, Yves Normandin, and Pierre Plamondon. Towards an Automatic Dictation System for Translators: the Transtalk Project. In 3rd International Conference on Spoken Language Processing (ICSLP94), Yokohama, Japan, 1994.
  • Marc Dymetman. A Simple Transformation for Offline-Parsable Grammars and its Termination Properties. In Proceedings of COLING 94, Kyoto, Japan, August 1994.
  • Marc Dymetman. Quelques développements récents à la périphérie de la Traduction Automatique. In Actes du congres TALN-94, Marseille, France, April 1994.
  • Marc Dymetman. Inherently reversible grammars. In Tomek Strzalkowski, editor, Reversible Grammar in Natural Language Processing. Kluwer Academic Publishers, Dordrecht, Holland, 1994.
  • Pierre Isabelle, Marc Dymetman, George Foster, Jean-Marc Jutras, Elliott Macklovitch, Francois Perrault, Xiaobo Ren, and Michel Simard. Translation Analysis and Translation Automation. In Proc. Fifth International Conference on Theoretical and Methodological Issues in Machine Translation, Kyoto, 1993.
  • Marc Dymetman. Transformations de grammaires logiques et reversibilite en Traduction Automatique. Thèse d'État, 1992. Universite Joseph Fourier (Grenoble 1), Grenoble, France.
  • Marc Dymetman. A Generalized Greibach Normal Form for Definite Clause Grammars. In Proceedings of COLING 92, volume 1, pages 366--372, Nantes, France, July 1992.
  • Marc Dymetman, George Foster, and Pierre Isabelle. Towards an Automatic Dictation System for Translators (TransTalk). Technical report, Ministere des Communications Canada, Centre Canadien de Recherches sur l'Informatisation du Travail, Laval, Quebec, 1992.
  • Marc Dymetman. Inherently Reversible Grammars, Logic Programming, and Computability. In Proceedings of the ACL Workshop: Reversible Grammar in Natural Language Processing, pages 20--30, Berkeley, CA, June 1991.
  • Marc Dymetman. A Generalized Greibach Normal Form for Definite Clause Grammars and the decidability of the offline-parsability problem, May 1991. Paper presented at the Second Meeting on the Mathematics of Language (MOL'2), Yorktown Heights, NY.
  • Marc Dymetman, Pierre Isabelle, and Francois Perrault. A symmetrical approach to parsing and generation. In Proceedings of the 13th International Conference on Computational Linguistics (COLING 90), volume 3, pages 90--96, Helsinki, August 1990.
  • Marc Dymetman and Pierre Isabelle. Grammar bidirectionality through controlled backward deduction. In P. Saint-Dizier and S. Szpakowicz, editors, Logic and Logic Grammars for Language Processing. Ellis Horwood, Chichester, England, 1990.
  • Marc Dymetman. Disambiguation and the difficulties of generation: A personal comment on one aspect of the workshop. In E. Blanc and Ch. Boitet, editors, Proceedings of DBMT-90, pages 248--251, GETA-IMAG, Grenoble, France, August 1990. Post-COLING seminar on Dialog-Based Machine Translation.
  • Pierre Isabelle, Jean-Luc Cochard, Marc Dymetman, Elliott Macklovitch, Francois Perrault, and Michel Simard. CRITTER: Un système de traduction pour les rapports de marches agricoles. In Proceedings of the Canadian Conference on Electrical and Computer Engineering, Montreal, September 1989.
  • Marc Dymetman and Pierre Isabelle. Reversible logic grammars for machine translation. In Proceedings of the Second International Conference on Theoretical and Methodological Issues in Machine Translation of Natural Languages, Pittsburgh, PA, June 1988. Carnegie Mellon University.
  • Pierre Isabelle, Marc Dymetman, and Elliott Macklovitch. CRITTER: a translation system for agricultural market reports. In Proceedings of the 12th International Conference on Computational Linguistics (COLING 88), pages 261--266, Budapest, August 1988.
  • Marc Dymetman. Two approaches to commonsense inferencing for discourse analysis. In Proceedings of the 11th International Conference on Computational Linguistics (COLING 86), pages 511--514, Bonn, August 1986.
  • Marc Dymetman. Inférence d'objets bi-dimensionnels a partir d'indices visuels locaux. In Actes du 3ème congrès AFCET Reconnaissance des Formes et Intelligence Artificielle, Nancy, France, 1981.

Invited Talks, Seminars

  • Marc Dymetman. Rédaction Sémantiquement Guidée de Documents Multilingues dans des Domaines Restreints. Invited Talk Séminaire Industries de la Langue, Grenoble Jan. 2001.
  • Marc Dymetman. Théorie des Groupes et Linguistique Computationnelle. Invited talk at LIM (Laboratoire Informatique de Marseille), January 2000.
  • Marc Dymetman. Linguistique computationnelle: analyse et génération d'énoncés à l'aide de diagrammes de Van Kampen. Séminaire IRISA, Rennes, Novembre 1999.
  • Marc Dymetman. Le principe d'entropie maximum et l'inférence dans les graphes probabilistes. Exposé au séminaire IRIA sur la Théorie de l'Information (organizers: B. Bouchon, J. Sallantin), Paris, 1980.

PATENTS

Granted Patents (with co-inventors)

US 7,593,144 Controlling scanning and copying devices through implicit gestures

US 7,543,758 Document localization of pointing actions using disambiguated visual regions

US 7,542,893 Machine translation using elastic chunks

US 7,536,295 Machine translation using non-contiguous fragments of text

US 7,495,792 Programmable physical document

US 7,383,171 Semantic stenography using short note input data

US 6,901,360 System and method for transferring packed linguistic structures

US 6,820,815 Encoded sheet material

US 6,752,317 Marking medium area with encoded identifier for producing action through network

US 6,665,490 Obtaining and using data associating annotating activities with portions of recordings

US 6,622,123 Interactive translation system and method

US 6,604,875 Authenticated sheet material

US 6,585,163 Encoded sheet material and system for processing

US 6,582,138 Authenticated sheet material

US 6,345,304 Obtaining network addresses from identifiers

US 6,330,976 Marking medium area with encoded identifier for producing action through network

Published Patent Applications (with co-inventors)

US. APP. 20080281857 Event hierarchies and memory organization for structured data retrieval

US. APP. 20070033002 Second language writing advisor

US. APP. 20060136223 Bilingual authoring assistant for the "tip of the tongue" problem

US. APP. 20050137847 Method and apparatus for language learning via controlled text authoring