The LIG English to French Machine Translation System for IWSLT 2012

Laurent Besacier (1) , Benjamin Lecouteux (1) , Marwen Azouzi (1) , Quang Luong Ngoc (1)

1 GETALP - Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole

This paper presents the LIG participation to the E-F MT task of IWSLT 2012. The primary system proposed made a large improvement (more than 3 point of BLEU on tst2010 set) compared to our last year participation. Part of this improv-ment was due to the use of an extraction from the Giga-word corpus. We also propose a preliminary adaptation of the driven decoding concept for machine translation. This method allows an efficient combination of machine translation systems, by rescoring the log-linear model at the N-best list level according to auxiliary systems: the basis technique is essentially guiding the search using one or previous system outputs. The results show that the approach allows a significant improvement in BLEU score using Google translate to guide our own SMT system. We also try to use a confidence measure as an additional log-linear feature but we could not get any improvment with this technique.

Domaines: Intelligence artificielle [cs.AI]; Informatique et langage [cs.CL]

Laurent Besacier, Benjamin Lecouteux, Marwen Azouzi, Quang Luong Ngoc. The LIG English to French Machine Translation System for IWSLT 2012. 9th International Workshop on Spoken Language Translation (IWSLT), Dec 2012, Hong Kong, China. pp.102-108. ⟨hal-00954211⟩