Lexically Constrained Neural Machine Translation with Levenshtein Transformer

Raymond Hendy Susanto, Shamil Chollampatt, Liling Tan


Abstract
This paper proposes a simple and effective algorithm for incorporating lexical constraints in neural machine translation. Previous work either required re-training existing models with the lexical constraints or incorporating them during beam search decoding with significantly higher computational overheads. Leveraging the flexibility and speed of a recently proposed Levenshtein Transformer model (Gu et al., 2019), our method injects terminology constraints at inference time without any impact on decoding speed. Our method does not require any modification to the training procedure and can be easily applied at runtime with custom dictionaries. Experiments on English-German WMT datasets show that our approach improves an unconstrained baseline and previous approaches.
Anthology ID:
2020.acl-main.325
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3536–3543
Language:
URL:
https://aclanthology.org/2020.acl-main.325
DOI:
10.18653/v1/2020.acl-main.325
Bibkey:
Cite (ACL):
Raymond Hendy Susanto, Shamil Chollampatt, and Liling Tan. 2020. Lexically Constrained Neural Machine Translation with Levenshtein Transformer. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3536–3543, Online. Association for Computational Linguistics.
Cite (Informal):
Lexically Constrained Neural Machine Translation with Levenshtein Transformer (Susanto et al., ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2020.acl-main.325.pdf
Video:
 http://slideslive.com/38928773
Code
 raymondhs/constrained-levt
Data
WMT 2014