Neural Baselines for Word Alignments - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Neural Baselines for Word Alignments

Anh Khoa Ngo Ho
François Yvon

Résumé

Word alignments identify translational correspondences between words in a parallel sentence pair and is used, for instance, to learn bilingual dictionaries, to train statistical machine translation systems, or to perform quality estimation. In most areas of natural language processing, neural network models nowadays constitute the preferred approach, a situation that might also apply to word alignment models. In this work, we study and comprehensively evaluate neural models for unsupervised word alignment for four language pairs, contrasting several variants of neural models. We show that in most settings, neural versions of the IBM-1 and hidden Markov models vastly outperform their discrete counterparts. We also analyze typical alignment errors of the baselines that our models overcome to illustrate the benefits --- and the limitations --- of these new models for morphologically rich languages.
Fichier principal
Vignette du fichier
IWSLT2019_paper_23.pdf (303.81 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02343217 , version 1 (02-11-2019)

Identifiants

Citer

Anh Khoa Ngo Ho, François Yvon. Neural Baselines for Word Alignments. International Workshop on Spoken Language Translation, Nov 2019, Hong-Kong, China. ⟨hal-02343217⟩
172 Consultations
293 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More