Point, Disambiguate and Copy: Incorporating Bilingual Dictionaries for Neural Machine Translation

Tong Zhang, Long Zhang, Wei Ye, Bo Li, Jinan Sun, Xiaoyu Zhu, Wen Zhao, Shikun Zhang


Abstract
This paper proposes a sophisticated neural architecture to incorporate bilingual dictionaries into Neural Machine Translation (NMT) models. By introducing three novel components: Pointer, Disambiguator, and Copier, our method PDC achieves the following merits inherently compared with previous efforts: (1) Pointer leverages the semantic information from bilingual dictionaries, for the first time, to better locate source words whose translation in dictionaries can potentially be used; (2) Disambiguator synthesizes contextual information from the source view and the target view, both of which contribute to distinguishing the proper translation of a specific source word from multiple candidates in dictionaries; (3) Copier systematically connects Pointer and Disambiguator based on a hierarchical copy mechanism seamlessly integrated with Transformer, thereby building an end-to-end architecture that could avoid error propagation problems in alternative pipe-line methods. The experimental results on Chinese-English and English-Japanese benchmarks demonstrate the PDC’s overall superiority and effectiveness of each component.
Anthology ID:
2021.acl-long.307
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long 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:
3970–3979
Language:
URL:
https://aclanthology.org/2021.acl-long.307
DOI:
10.18653/v1/2021.acl-long.307
Bibkey:
Cite (ACL):
Tong Zhang, Long Zhang, Wei Ye, Bo Li, Jinan Sun, Xiaoyu Zhu, Wen Zhao, and Shikun Zhang. 2021. Point, Disambiguate and Copy: Incorporating Bilingual Dictionaries for Neural Machine Translation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 3970–3979, Online. Association for Computational Linguistics.
Cite (Informal):
Point, Disambiguate and Copy: Incorporating Bilingual Dictionaries for Neural Machine Translation (Zhang et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.307.pdf
Video:
 https://aclanthology.org/2021.acl-long.307.mp4