Investigations on Translation Model Adaptation Using Monolingual Data - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2011

Investigations on Translation Model Adaptation Using Monolingual Data

Résumé

Most of the freely available parallel data to train the translation model of a statistical machine translation system comes from very specific sources (European parliament, United Nations, etc). Therefore, there is increasing interest in methods to perform an adaptation of the translation model. A popular approach is based on unsupervised training, also called self-enhancing. Both only use monolingual data to adapt the translation model. In this paper we extend the previous work and provide new insight in the existing methods. We report results on the translation between French and English. Improvements of up to 0.5 BLEU were observed with respect to a very competitive baseline trained on more than 280M words of human translated parallel data.
Fichier principal
Vignette du fichier
11_07_wmt_adaptationWithMonolingualData.pdf (88.45 Ko) Télécharger le fichier
11_07_wmt_adaptationWithMonolingualData.slides.pdf (284.42 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Format : Autre

Dates et versions

hal-00625481 , version 1 (21-09-2011)

Identifiants

  • HAL Id : hal-00625481 , version 1

Citer

Patrik Lambert, Holger Schwenk, Christophe Servan, Sadaf Abdul-Rauf. Investigations on Translation Model Adaptation Using Monolingual Data. Sixth Workshop on Statistical Machine Translation, Jul 2011, Edinburgh, United Kingdom. pp.284-293. ⟨hal-00625481⟩

Relations

433 Consultations
276 Téléchargements

Partager

Gmail Facebook X LinkedIn More