Priming Neural Machine Translation - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Priming Neural Machine Translation

Minh Quang Pham
Jitao Xu
  • Fonction : Auteur
  • PersonId : 184998
  • IdHAL : xujitao
Josep-Maria Crego
  • Fonction : Auteur
  • PersonId : 1038144
Jean Senellart
  • Fonction : Auteur
  • PersonId : 1038145
François Yvon

Résumé

Priming is a well known and studied psychology phenomenon based on the prior presentation of one stimulus (cue) to influence the processing of a response. In this paper, we propose a framework to mimic the process of priming in the context of neural machine translation (NMT). We evaluate the effect of using similar translations as priming cues on the NMT network. We propose a method to inject priming cues into the NMT network and compare our framework to other mechanisms that perform micro-adaptation during inference. Overall, experiments conducted in a multi-domain setting confirm that adding priming cues in the NMT decoder can go a long way towards improving the translation accuracy. Besides, we show the suitability of our framework to gather valuable information for an NMT network from monolingual resources.
Fichier principal
Vignette du fichier
2020.wmt-1.63.pdf (522.14 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03013196 , version 1 (19-11-2020)

Identifiants

  • HAL Id : hal-03013196 , version 1

Citer

Minh Quang Pham, Jitao Xu, Josep-Maria Crego, Jean Senellart, François Yvon. Priming Neural Machine Translation. Conference on Machine Translation, Nov 2020, Online, United States. ⟨hal-03013196⟩
244 Consultations
105 Téléchargements

Partager

Gmail Facebook X LinkedIn More