LIUM's SMT Machine Translation Systems for WMT 2012
Résumé
This paper describes the development of French–English and English–French statistical machine translation systems for the 2012 WMT shared task evaluation. We developed phrase-based systems based on the Moses de-coder, trained on the provided data only. Additionally , new features this year included improved language and translation model adaptation using the cross-entropy score for the corpus selection.
Domaines
| Origine | Fichiers éditeurs autorisés sur une archive ouverte |
|---|---|
| Licence |
![]()
Fait partie de hal-01157949 Article Christophe Servan, Holger Schwenk. Optimising Multiple Metrics with MERT. The Prague Bulletin of Mathematical Linguistics, 2011, 96, pp.109. ⟨hal-01157949⟩