A Template-based Method for Constrained Neural Machine Translation

Shuo Wang, Peng Li, Zhixing Tan, Zhaopeng Tu, Maosong Sun, Yang Liu


Abstract
Machine translation systems are expected to cope with various types of constraints in many practical scenarios. While neural machine translation (NMT) has achieved strong performance in unconstrained cases, it is non-trivial to impose pre-specified constraints into the translation process of NMT models. Although many approaches have been proposed to address this issue, most existing methods can not satisfy the following three desiderata at the same time: (1) high translation quality, (2) high match accuracy, and (3) low latency. In this work, we propose a template-based method that can yield results with high translation quality and match accuracy and the inference speed of our method is comparable with unconstrained NMT models. Our basic idea is to rearrange the generation of constrained and unconstrained tokens through a template. Our method does not require any changes in the model architecture and the decoding algorithm. Experimental results show that the proposed template-based approach can outperform several representative baselines in both lexically and structurally constrained translation tasks.
Anthology ID:
2022.emnlp-main.240
Original:
2022.emnlp-main.240v1
Version 2:
2022.emnlp-main.240v2
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3665–3679
Language:
URL:
https://aclanthology.org/2022.emnlp-main.240
DOI:
10.18653/v1/2022.emnlp-main.240
Bibkey:
Cite (ACL):
Shuo Wang, Peng Li, Zhixing Tan, Zhaopeng Tu, Maosong Sun, and Yang Liu. 2022. A Template-based Method for Constrained Neural Machine Translation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3665–3679, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
A Template-based Method for Constrained Neural Machine Translation (Wang et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.240.pdf