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.
BibTeX
@inproceedings{zeng-etal-2022-neighbors,
title = "Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraints",
author = "Zeng, Chun and
Chen, Jiangjie and
Zhuang, Tianyi and
Xu, Rui and
Yang, Hao and
Ying, Qin and
Tao, Shimin and
Xiao, Yanghua",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.424/",
doi = "10.18653/v1/2022.naacl-main.424",
pages = "5777--5790"
}