Graph Neural Networks for Multiparallel Word Alignment - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Graph Neural Networks for Multiparallel Word Alignment

Résumé

After a period of decrease, interest in word alignments is increasing again for their usefulness in domains such as typological research, cross-lingual annotation projection and machine translation. Generally, alignment algorithms only use bitext and do not make use of the fact that many parallel corpora are multiparallel. Here, we compute high-quality word alignments between multiple language pairs by considering all language pairs together. First, we create a multiparallel word alignment graph, joining all bilingual word alignment pairs in one graph. Next, we use graph neural networks (GNNs) to exploit the graph structure. Our GNN approach (i) utilizes information about the meaning, position and language of the input words, (ii) incorporates information from multiple parallel sentences, (iii) adds and removes edges from the initial alignments, and (iv) yields a prediction model that can generalize beyond the training sentences. We show that community detection provides valuable information for multiparallel word alignment. Our method outperforms previous work on three word alignment datasets and on a downstream task.
Fichier principal
Vignette du fichier
2022.findings-acl.108.pdf (731.73 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03679419 , version 1 (26-05-2022)

Identifiants

  • HAL Id : hal-03679419 , version 1

Citer

Ayyoob Imani, Lütfi Şenel, Masoud Sabet, François Yvon, Hinrich Schütze. Graph Neural Networks for Multiparallel Word Alignment. Findings of the ACL: ACL 2022, The Association for Computational Linguistics (ACL), May 2022, Dublin, Ireland. ⟨hal-03679419⟩
54 Consultations
38 Téléchargements

Partager

Gmail Facebook X LinkedIn More