Knowledge Distillation for Multilingual Unsupervised Neural Machine Translation

Haipeng Sun, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, Tiejun Zhao


Abstract
Unsupervised neural machine translation (UNMT) has recently achieved remarkable results for several language pairs. However, it can only translate between a single language pair and cannot produce translation results for multiple language pairs at the same time. That is, research on multilingual UNMT has been limited. In this paper, we empirically introduce a simple method to translate between thirteen languages using a single encoder and a single decoder, making use of multilingual data to improve UNMT for all language pairs. On the basis of the empirical findings, we propose two knowledge distillation methods to further enhance multilingual UNMT performance. Our experiments on a dataset with English translated to and from twelve other languages (including three language families and six language branches) show remarkable results, surpassing strong unsupervised individual baselines while achieving promising performance between non-English language pairs in zero-shot translation scenarios and alleviating poor performance in low-resource language pairs.
Anthology ID:
2020.acl-main.324
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3525–3535
Language:
URL:
https://aclanthology.org/2020.acl-main.324
DOI:
10.18653/v1/2020.acl-main.324
Bibkey:
Cite (ACL):
Haipeng Sun, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, and Tiejun Zhao. 2020. Knowledge Distillation for Multilingual Unsupervised Neural Machine Translation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3525–3535, Online. Association for Computational Linguistics.
Cite (Informal):
Knowledge Distillation for Multilingual Unsupervised Neural Machine Translation (Sun et al., ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/2020.acl-main.324.pdf
Video:
 http://slideslive.com/38928849