Continuous space translation models with neural networks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

Continuous space translation models with neural networks

Résumé

The use of conventional maximum likelihood estimates hinders the performance of existing phrase-based translation models. For lack of sufficient training data, most models only consider a small amount of context. As a partial remedy, we explore here several continuous space translation models, where translation probabilities are estimated using a continuous representation of translation units in lieu of standard discrete representations. In order to handle a large set of translation units, these representations and the associated estimates are jointly computed using a multi-layer neural network with a SOUL architecture. In small scale and large scale English to French experiments, we show that the resulting models can effectively be trained and used on top of a n-gram translation system, delivering significant improvements in performance.
Fichier principal
Vignette du fichier
N12-1005.pdf (214.62 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-01960659 , version 1 (08-01-2019)

Identifiants

  • HAL Id : hal-01960659 , version 1

Citer

Le Hai Son, Alexandre Allauzen, François Yvon. Continuous space translation models with neural networks. Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Jun 2012, Montréal, Canada. ⟨hal-01960659⟩
183 Consultations
60 Téléchargements

Partager

Gmail Facebook X LinkedIn More