Communication Dans Un Congrès Année : 2013

LIMSI @ WMT'13

Hai-Son Le
  • Fonction : Auteur
  • PersonId : 1038150
  • IdRef : 166731226

Résumé

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.

Fichier principal
Vignette du fichier
WMT13.pdf (202.59 Ko) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Licence
Loading...

Dates et versions

hal-01489998 , version 1 (15-03-2017)

Licence

Identifiants

  • HAL Id : hal-01489998 , version 1

Citer

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⟩
247 Consultations
269 Téléchargements

Partager

  • More