Iterative Nearest Neighbour Machine Translation for Unsupervised Domain Adaptation

Hui Huang, Shuangzhi Wu, Xinnian Liang, Zefan Zhou, Muyun Yang, Tiejun Zhao


Abstract
Unsupervised domain adaptation of machine translation, which adapts a pre-trained translation model to a specific domain without in-domain parallel data, has drawn extensive attention in recent years. However, most existing methods focus on the fine-tuning based techniques, which is non-extensible. In this paper, we propose a new method to perform unsupervised domain adaptation in a non-parametric manner. Our method only resorts to in-domain monolingual data, and we jointly perform nearest neighbour inference on both forward and backward translation directions. The forward translation model creates nearest neighbour datastore for the backward direction, and vice versa, strengthening each other in an iterative style. Experiments on multi-domain datasets demonstrate that our method significantly improves the in-domain translation performance and achieves state-of-the-art results among non-parametric methods.
Anthology ID:
2023.findings-acl.840
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13294–13301
Language:
URL:
https://aclanthology.org/2023.findings-acl.840
DOI:
10.18653/v1/2023.findings-acl.840
Bibkey:
Cite (ACL):
Hui Huang, Shuangzhi Wu, Xinnian Liang, Zefan Zhou, Muyun Yang, and Tiejun Zhao. 2023. Iterative Nearest Neighbour Machine Translation for Unsupervised Domain Adaptation. In Findings of the Association for Computational Linguistics: ACL 2023, pages 13294–13301, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Iterative Nearest Neighbour Machine Translation for Unsupervised Domain Adaptation (Huang et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.840.pdf