Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction

Gyubok Lee, Seongjun Yang, Edward Choi


Abstract
Accurate terminology translation is crucial for ensuring the practicality and reliability of neural machine translation (NMT) systems. To address this, lexically constrained NMT explores various methods to ensure pre-specified words and phrases appear in the translation output. However, in many cases, those methods are studied on general domain corpora, where the terms are mostly uni- and bi-grams (>98%). In this paper, we instead tackle a more challenging setup consisting of domain-specific corpora with much longer n-gram and highly specialized terms. Inspired by the recent success of masked span prediction models, we propose a simple and effective training strategy that achieves consistent improvements on both terminology and sentence-level translation for three domain-specific corpora in two language pairs.
Anthology ID:
2021.acl-short.94
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
743–753
Language:
URL:
https://aclanthology.org/2021.acl-short.94
DOI:
10.18653/v1/2021.acl-short.94
Bibkey:
Cite (ACL):
Gyubok Lee, Seongjun Yang, and Edward Choi. 2021. Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 743–753, Online. Association for Computational Linguistics.
Cite (Informal):
Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction (Lee et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-short.94.pdf
Video:
 https://aclanthology.org/2021.acl-short.94.mp4
Code
 wns823/NMT_SSP