LIMSI @ WMT'13

Alexandre Allauzen (1) , Nicolas Pécheux (1) , Quoc Khanh Do (1) , Marco Dinarelli (2, 3, 4, 5) , Thomas Lavergne (1) , Aurélien Max (1) , Hai-Son Le (6) , François Yvon (1)

1 LIMSI - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur
2 ENS-PSL - École normale supérieure - Paris
3 USPC - Université Sorbonne Paris Cité
4 PSL - Université Paris Sciences et Lettres
5 Lattice - Lattice - Langues, Textes, Traitements informatiques, Cognition - UMR 8094
6 University of Calgary

This paper describes LIMSI's submissions to the shared WMT'13 translation task. We report results for French-English, German-English and Spanish-English in both directions. Our submissions use n-code, an open source system based on bilingual n-grams, and continuous space models in a post-processing step. The main novelties of this year's participation are the following: our first participation to the Spanish-English task; experiments with source pre-ordering; a tighter integration of continuous space language models using artificial text generation (for Ger-man); and the use of different tuning sets according to the original language of the text to be translated.

Mots clés: Machine Translation; Reordering techniques

Domaines: Informatique et langage [cs.CL]; Apprentissage [cs.LG]

Alexandre Allauzen, Nicolas Pécheux, Quoc Khanh Do, Marco Dinarelli, Thomas Lavergne, et al.. LIMSI @ WMT'13. Workshop on Statistical Machine Translation 2013 (WMT 13), Aug 2013, Sofia, Bulgaria. pp.62 - 69. ⟨hal-01489998⟩