Bilingual Synchronization: Restoring Translational Relationships with Editing Operations

Jitao Xu (1) , Josep Crego (2) , François Yvon (1)

1 TLP - Traitement du Langage Parlé - LISN
2 SYSTRAN

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.

Domains: Computation and Language [cs.CL]

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. ⟨hal-03827010⟩