Generative latent neural models for automatic word alignment - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Generative latent neural models for automatic word alignment

Anh Khoa Ngo Ho
François Yvon

Résumé

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.
Fichier principal
Vignette du fichier
amta2020.pdf (256.45 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-02949042 , version 1 (25-09-2020)

Identifiants

  • HAL Id : hal-02949042 , version 1

Citer

Anh Khoa Ngo Ho, François Yvon. Generative latent neural models for automatic word alignment. Association for Machine Translation in the Americas, Oct 2020, Miami, Florida, United States. pp.64-77. ⟨hal-02949042⟩
113 Consultations
112 Téléchargements

Partager

Gmail Facebook X LinkedIn More