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

Boosting Neural Machine Translation with Similar Translations

Josep-Maria Crego
  • Fonction : Auteur
  • PersonId : 1038144
Jean Senellart
  • Fonction : Auteur
  • PersonId : 1038145

Résumé

This paper explores data augmentation methods for training Neural Machine Translation to make use of similar translations, in a comparable way a human translator employs fuzzy matches. In particular, we show how we can simply feed the neural model with information on both source and target sides of the fuzzy matches, we also extend the similarity to include semantically related translations retrieved using distributed sentence representations. We show that translations based on fuzzy matching provide the model with "copy" information while translations based on embedding similarities tend to extend the translation "context". Results indicate that the effect from both similar sentences are adding up to further boost accuracy, are combining naturally with model fine-tuning and are providing dynamic adaptation for unseen translation pairs. Tests on multiple data sets and domains show consistent accuracy improvements. To foster research around these techniques, we also release an Open-Source toolkit with efficient and flexible fuzzy-match implementation.
Fichier principal
Vignette du fichier
2020.acl-main.144.pdf (346.35 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-02956324 , version 1 (02-10-2020)

Identifiants

Citer

Jitao Xu, Josep-Maria Crego, Jean Senellart. Boosting Neural Machine Translation with Similar Translations. Annual Meeting of the Association for Computational Linguistics, Jul 2020, Seattle, United States. pp.1570-1579, ⟨10.18653/v1/2020.acl-main.143⟩. ⟨hal-02956324⟩
322 Consultations
252 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More