Martine Smets


2005

pdf bib
Sentence-level MT evaluation without reference translations: beyond language modeling
Michael Gamon | Anthony Aue | Martine Smets
Proceedings of the 10th EAMT Conference: Practical applications of machine translation

2004

pdf bib
Linguistically Informed Statistical Models of Constituent Structure for Ordering in Sentence Realization
Eric Ringger | Michael Gamon | Robert C. Moore | David Rojas | Martine Smets | Simon Corston-Oliver
COLING 2004: Proceedings of the 20th International Conference on Computational Linguistics

2003

pdf bib
French Amalgam: A machine-learned sentence realization system
Martine Smets | Michael Gamon | Simon Corston-Oliver | Eric Ringger
Actes de la 10ème conférence sur le Traitement Automatique des Langues Naturelles. Articles longs

This paper presents the French implementation of Amalgam, a machine-learned sentence realization system. It presents in some detail two of the machine-learned models employed in Amalgam and shows how linguistic intuition and knowledge can be combined with statistical techniques to improve the performance of the models.

pdf bib
French Amalgam: a quick adaptation of a sentence realization system to French
Martine Smets | Michael Gamon | Simon Corston-Oliver | Eric Ringger
10th Conference of the European Chapter of the Association for Computational Linguistics

pdf bib
High quality machine translation using a machine-learned sentence realization component
Martine Smets | Michael Gamon | Jessie Pinkham | Tom Reutter | Martine Pettenaro
Proceedings of Machine Translation Summit IX: Papers

We describe the implementation of two new language pairs (English-French and English-German) which use machine-learned sentence realization components instead of hand-written generation components. The resulting systems are evaluated by human evaluators, and in the technical domain, are equal to the quality of highly respected commercial systems. We comment on the difficulties that are encountered when using machine-learned sentence realization in the context of MT.

2002

pdf bib
Machine translation without a bilingual dictionary
Jessie Pinkham | Martine Smets
Proceedings of the 9th Conference on Theoretical and Methodological Issues in Machine Translation of Natural Languages: Papers

pdf bib
Modular MT with a Learned Bilingual Dictionary: Rapid Deployment of a New Language Pair
Jessie Pinkham | Martine Smets
COLING 2002: The 19th International Conference on Computational Linguistics

pdf bib
Machine Translation as a Testbed for Multilingual Analysis
Richard Campbell | Carmen Lozano | Jessie Pinkham | Martine Smets
COLING-02: Grammar Engineering and Evaluation

pdf bib
Traduction automatique ancrée dans l’analyse linguistique
Jessie Pinkham | Martine Smets
Actes de la 9ème conférence sur le Traitement Automatique des Langues Naturelles. Articles longs

Nous présentons dans cet article le système de traduction français-anglais MSR-MT développé à Microsoft dans le groupe de recherche sur le traitement du language (NLP). Ce système est basé sur des analyseurs sophistiqués qui produisent des formes logiques, dans la langue source et la langue cible. Ces formes logiques sont alignées pour produire la base de données du transfert, qui contient les correspondances entre langue source et langue cible, utilisées lors de la traduction. Nous présentons différents stages du développement de notre système, commencé en novembre 2000. Nous montrons que les performances d’octobre 2001 de notre système sont meilleures que celles du système commercial Systran, pour le domaine technique, et décrivons le travail linguistique qui nous a permis d’arriver à cette performance. Nous présentons enfin les résultats préliminaires sur un corpus plus général, les débats parlementaires du corpus du Hansard. Quoique nos résultats ne soient pas aussi concluants que pour le domaine technique, nous sommes convaincues que la résolution des problèmes d’analyse que nous avons identifiés nous permettra d’améliorer notre performance.

2001

pdf bib
Rapid assembly of a large-scale French-English MT system
Jessie Pinkham | Monica Corston-Oliver | Martine Smets | Martine Pettenaro
Proceedings of Machine Translation Summit VIII

Past research has shown that the ideal MT system should be modular and devoid of language pair specific information in its design. We describe here the assembly of TAMTAM (Traduction Automatique Microsoft), the French-English research MT system under development at Microsoft, which was constructed from a combination of pre-existing rule-based components and automatically created components. At this stage, the system has not been adapted either computationally or linguistically to the French-English context and yet it performs only slightly below the French-English Systran system in independent blind human evaluations

2000

pdf bib
Engineering a Wide-Coverage Lexicalized Grammar
John Carroll | Nicolas Nicolov | Olga Shaumyan | Martine Smets | David Weir
Proceedings of the Fifth International Workshop on Tree Adjoining Grammar and Related Frameworks (TAG+5)

1999

pdf bib
Parsing with an Extended Domain of Locality
John Carroll | Nicolas Nicolov | Olga Shaumyan | Martine Smets | David Weir
Ninth Conference of the European Chapter of the Association for Computational Linguistics

1998

pdf bib
The LexSys project
John Carroll | Nicolas Nicolov | Olga Shaumyan | Martine Smets | David Weir
Proceedings of the Fourth International Workshop on Tree Adjoining Grammars and Related Frameworks (TAG+4)

pdf bib
Comparison of XTAG and LEXSYS grammars
Martine Smets
Proceedings of the Fourth International Workshop on Tree Adjoining Grammars and Related Frameworks (TAG+4)

pdf bib
A compact encoding of a DTG grammar
Martine Smets | Roger Evans
Proceedings of the Fourth International Workshop on Tree Adjoining Grammars and Related Frameworks (TAG+4)

pdf bib
Paradigmatic Treatment of Arabic Morphology
Martine Smets
Computational Approaches to Semitic Languages