Mixing multiple translation models in statistical machine translation

Auteur	Rechercher : Razmara, Majid; Rechercher : Foster, George¹; Rechercher : Sankaran, Baskaran; Rechercher : Sarkar, Anoop
Affiliation	Conseil national de recherches du Canada
Format	Texte, Article
Conférence	50th Annual Meeting of the Association for Computational Linguistics (ACL 2012), Jeju Island, Republic of Korea, 8-14 July, 2012
Résumé	Statistical machine translation is often faced with the problem of combining training data from many diverse sources into a single translation model which then has to translate sentences in a new domain. We propose a novel approach, ensemble decoding, which combines a number of translation systems dynamically at the decoding step. In this paper, we evaluate performance on a domain adaptation setting where we translate sentences from the medical domain. Our experimental results show that ensemble decoding outperforms various strong baselines including mixture models, the current state-of-the-art for domain adaptation in machine translation.
Date de publication	2012-07
Dans	Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (juillet 2012).
Langue	anglais
Publications évaluées par des pairs	Oui
Numéro NPARC	20494947
Exporter la notice	Exporter en format RIS
Signaler une correction	Signaler une correction (s'ouvre dans un nouvel onglet)
Identificateur de l’enregistrement	3a79c192-af06-4ff4-84a8-fbc03003c772
Enregistrement créé	2012-08-16
Enregistrement modifié	2020-04-21