Abstract : 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.
https://hal.archives-ouvertes.fr/hal-00959143 Contributor : Laurent BesacierConnect in order to contact the contributor Submitted on : Monday, November 27, 2017 - 10:24:31 AM Last modification on : Thursday, October 21, 2021 - 3:50:27 AM
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⟩