The LIGA machine translation system for WMT 2011

This paper describes the system submitted by the Laboratory of Informatics of Grenoble (LIG) for the fifth Workshop on Statistical Machine Translation. We participated to the news shared translation task for the French-English language pair. We investigated differents techniques to simply deal with Out-Of-Vocabulary words in a statistical phrase-based machine translation system and analyze their impact on translation quality. The final submission is a combination between a standard phrase-based system using the Moses decoder, with appropriate setups and pre-processing, and a lemmatized system to deal with Out-Of-Vocabulary conjugated verbs.

Domaines

Informatique et langage [cs.CL]

Fichier principal

Potet et al 2011.pdf (102.39 Ko)

Origine	Fichiers éditeurs autorisés sur une archive ouverte

Laurent Besacier : Connectez-vous pour contacter le contributeur

https://hal.science/hal-00959143

Soumis le : lundi 27 novembre 2017-10:24:31

Dernière modification le : mercredi 18 décembre 2024-09:43:37

Dates et versions

hal-00959143 , version 1 (27-11-2017)

Identifiants

HAL Id : hal-00959143 , version 1

Citer

Marion Potet, Raphaël Rubino, Benjamin Lecouteux, Stéphane Huet, Hervé Blanchon, et al.. The LIGA machine translation system for WMT 2011. EMNLP 2011 SIXTH WORKSHOP ON STATISTICAL MACHINE TRANSLATION , 2011, Edinburgh United Kingdom. ⟨hal-00959143⟩

Exporter

BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite

Collections

UNIV-AVIGNON UGA CNRS LIG LIG_TDCGE LIG_TDCGE_GETALP LIA POLYTECH-GRENOBLE LIG_SIDCH

298 Consultations

76 Téléchargements