Restricted or Not: A General Training Framework for Neural Machine Translation

Zuchao Li, Masao Utiyama, Eiichiro Sumita, Hai Zhao


Abstract
Restricted machine translation incorporates human prior knowledge into translation. It restricts the flexibility of the translation to satisfy the demands of translation in specific scenarios. Existing work typically imposes constraints on beam search decoding. Although this can satisfy the requirements overall, it usually requires a larger beam size and far longer decoding time than unrestricted translation, which limits the concurrent processing ability of the translation model in deployment, and thus its practicality. In this paper, we propose a general training framework that allows a model to simultaneously support both unrestricted and restricted translation by adopting an additional auxiliary training process without constraining the decoding process. This maintains the benefits of restricted translation but greatly reduces the extra time overhead of constrained decoding, thus improving its practicality. The effectiveness of our proposed training framework is demonstrated by experiments on both original (WAT21 EnJa) and simulated (WMT14 EnDe and EnFr) restricted translation benchmarks.
Anthology ID:
2022.acl-srw.18
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Samuel Louvan, Andrea Madotto, Brielen Madureira
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
245–251
Language:
URL:
https://aclanthology.org/2022.acl-srw.18
DOI:
10.18653/v1/2022.acl-srw.18
Bibkey:
Cite (ACL):
Zuchao Li, Masao Utiyama, Eiichiro Sumita, and Hai Zhao. 2022. Restricted or Not: A General Training Framework for Neural Machine Translation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pages 245–251, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Restricted or Not: A General Training Framework for Neural Machine Translation (Li et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-srw.18.pdf
Data
ASPEC