Training Statistical Machine Translation with Multivariate Mutual Information - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2011

Training Statistical Machine Translation with Multivariate Mutual Information

Résumé

In this paper, we describe a new model for phrase-based statistical machine translation. Roughly speaking, statistical approach uses a language and a translation model. This latter could be viewed as a lexical and an alignment model. The approach we propose does not need any alignment, it is based on inter-lingual triggers determined by multivariate mutual information (MMI). This measure depends on conditional mutual information, this means that a source phrase is directly linked to a target one. The conditional mutual information is used in both directions (source-target and target-source languages). We present an experimental evaluation conducted on EUROPARL corpora (French and English) and using the decoder MOSES. We compare then our results to those of a previous work in which we used inter-lingual triggers determined by a simple mutual information (MI) as well as to those given by baseline model (Koehn et al., 2003).
Fichier principal
Vignette du fichier
LTC2011NasriSmailiLatiri.pdf (143.14 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01272104 , version 1 (10-02-2016)

Identifiants

  • HAL Id : hal-01272104 , version 1

Citer

Cyrine Nasri, Kamel Smaïli, Chiraz Latiri. Training Statistical Machine Translation with Multivariate Mutual Information. 5th Language and Technology Conference, Nov 2011, Poznan, Poland. ⟨hal-01272104⟩
114 Consultations
55 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More