Accéder directement au contenu Accéder directement à la navigation
Communication dans un congrès

Generative latent neural models for automatic word alignment

Anh Khoa Ngo Ho 1 François Yvon 1
1 TLP - Traitement du Langage Parlé
LIMSI - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur
Abstract : Word alignments identify translational correspondences between words in a parallel sentence pair and are used, for instance, to learn bilingual dictionaries, to train statistical machine translation systems or to perform quality estimation. Variational autoencoders have been recently used in various of natural language processing to learn in an unsupervised way latent representations that are useful for language generation tasks. In this paper, we study these models for the task of word alignment and propose and assess several evolutions of a vanilla variational autoencoders. We demonstrate that these techniques can yield competitive results as compared to Giza++ and to a strong neural network alignment system for two language pairs.
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-02949042
Contributeur : Anh Khoa Ngo Ho <>
Soumis le : vendredi 25 septembre 2020 - 12:07:17
Dernière modification le : mercredi 14 octobre 2020 - 04:21:59

Fichiers

amta2020.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-02949042, version 1
  • ARXIV : 2009.13117

Collections

Citation

Anh Khoa Ngo Ho, François Yvon. Generative latent neural models for automatic word alignment. The Association for Machine Translation in the Americas, Oct 2020, Florida, United States. ⟨hal-02949042⟩

Partager

Métriques

Consultations de la notice

34

Téléchargements de fichiers

13