Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraints

Chun Zeng, Jiangjie Chen, Tianyi Zhuang, Rui Xu, Hao Yang, Qin Ying, Shimin Tao, Yanghua Xiao


Abstract
Lexically constrained neural machine translation (NMT) draws much industrial attention for its practical usage in specific domains. However, current autoregressive approaches suffer from high latency. In this paper, we focus on non-autoregressive translation (NAT) for this problem for its efficiency advantage. We identify that current constrained NAT models, which are based on iterative editing, do not handle low-frequency constraints well. To this end, we propose a plug-in algorithm for this line of work, i.e., Aligned Constrained Training (ACT), which alleviates this problem by familiarizing the model with the source-side context of the constraints. Experiments on the general and domain datasets show that our model improves over the backbone constrained NAT model in constraint preservation and translation quality, especially for rare constraints.
Anthology ID:
2022.naacl-main.424
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5777–5790
Language:
URL:
https://aclanthology.org/2022.naacl-main.424
DOI:
10.18653/v1/2022.naacl-main.424
Bibkey:
Cite (ACL):
Chun Zeng, Jiangjie Chen, Tianyi Zhuang, Rui Xu, Hao Yang, Qin Ying, Shimin Tao, and Yanghua Xiao. 2022. Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraints. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5777–5790, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraints (Zeng et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.424.pdf
Video:
 https://aclanthology.org/2022.naacl-main.424.mp4
Code
 sted-byte/act4nat