Communication Dans Un Congrès Année : 2022

Bilingual Synchronization: Restoring Translational Relationships with Editing Operations

Jitao Xu
Josep Crego

Résumé

Machine Translation (MT) is usually viewed as a one-shot process that generates the target language equivalent of some source text from scratch. We consider here a more general setting which assumes an initial target sequence, that must be transformed into a valid translation of the source, thereby restoring parallelism between source and target. For this bilingual synchronization task, we consider several architectures (both autoregressive and non-autoregressive) and training regimes, and experiment with multiple practical settings such as simulated interactive MT, translating with Translation Memory (TM) and TM cleaning. Our results suggest that one single generic edit-based system, once fine-tuned, can compare with, or even outperform, dedicated systems specifically trained for these tasks.

Fichier principal
Vignette du fichier
emnlp_arxiv.pdf (336.03 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-03827010 , version 1 (24-10-2022)

Licence

Identifiants

Citer

Jitao Xu, Josep Crego, François Yvon. Bilingual Synchronization: Restoring Translational Relationships with Editing Operations. The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022), Dec 2022, Abou Dabi, United Arab Emirates. pp.8016-8030, ⟨10.18653/v1/2022.emnlp-main.548⟩. ⟨hal-03827010⟩
1834 Consultations
289 Téléchargements

Altmetric

Partager

  • More