LIMSI @ WMT11 - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2011

LIMSI @ WMT11

Résumé

This paper describes LIMSI's submissions to the Sixth Workshop on Statistical Machine Translation. We report results for the French-English and German-English shared translation tasks in both directions. Our systems use n-code, an open source Statistical Machine Translation system based on bilingual n-grams. For the French-English task, we focussed on finding efficient ways to take advantage of the large and heterogeneous training parallel data. In particular, using a simple filtering strategy helped to improve both processing time and translation quality. To translate from English to French and German, we also investigated the use of the SOUL language model in Machine Translation and showed significant improvements with a 10-gram SOUL model. We also briefly report experiments with several alternatives to the standard n-best MERT procedure, leading to a significant speed-up.
Fichier principal
Vignette du fichier
LIMSI_WMT11.pdf (180.26 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00644047 , version 1 (23-11-2011)

Identifiants

  • HAL Id : hal-00644047 , version 1

Citer

Alexandre Allauzen, Hélène Bonneau-Maynard, Hai-Son Le, Aurélien Max, Guillaume Wisniewski, et al.. LIMSI @ WMT11. Sixth Workshop on Statistical Machine Translation (WMT 11), Jul 2011, Edinburgh, United Kingdom. pp.309-315. ⟨hal-00644047⟩
184 Consultations
272 Téléchargements

Partager

Gmail Facebook X LinkedIn More