Investigations on Translation Model Adaptation Using Monolingual Data

Abstract : 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.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-00625481
Contributor : Patrik Lambert <>
Submitted on : Wednesday, September 21, 2011 - 4:36:06 PM
Last modification on : Friday, December 2, 2016 - 4:50:34 PM
Long-term archiving on : Tuesday, November 13, 2012 - 2:10:32 PM

Identifiers

  • HAL Id : hal-00625481, version 1

Collections

Citation

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⟩

Share

Metrics

Record views

436

Files downloads

335