Improving MT coherence through text- level processing of input texts: the COMTIS project. Session 6 - Translation and Natural Language Processing

Andrei Popescu-Belis (1) , Bruno Cartoni , Andrea Gesmundo , James Henderson , Cristina Grisot , Paola Merlo , Thomas Meyer , Jacques Moeschler (2) , Sandrine Zufferey (3)

1 IDIAP Research Institute
2 Département de linguistique, Université de Genève
3 Département de linguistique, Faculté des lettres, Université de Genève

This paper presents an ongoing research project, started in March 2010 and sponsored by the Swiss National Science Foundation, which aims at improving machine translation output in terms of textual coherence. Coherence in text is mainly due to inter-sentential dependencies. Statistical Machine Translation (SMT) systems, currently sentence-based, often fail to translate these dependencies correctly. Within the COMTIS project, state-of-the-art linguistics research and Natural Language Processing (NLP) techniques are combined to identify and to label inter-sentential dependencies that can be learned by SMT system in the training phase.

Mots clés: Tralogy I

Domaines: Informatique et langage [cs.CL]; Sciences de l'information et de la communication

Andrei Popescu-Belis, Bruno Cartoni, Andrea Gesmundo, James Henderson, Cristina Grisot, et al.. Improving MT coherence through text- level processing of input texts: the COMTIS project. Session 6 - Translation and Natural Language Processing. Tralogy I. Métiers et technologies de la traduction : quelles convergences pour l'avenir ?, Mar 2011, Paris, France. 14p. ⟨hal-02495992⟩