A Compact and Language-Sensitive Multilingual Translation Method

Yining Wang, Long Zhou, Jiajun Zhang, Feifei Zhai, Jingfang Xu, Chengqing Zong


Abstract
Multilingual neural machine translation (Multi-NMT) with one encoder-decoder model has made remarkable progress due to its simple deployment. However, this multilingual translation paradigm does not make full use of language commonality and parameter sharing between encoder and decoder. Furthermore, this kind of paradigm cannot outperform the individual models trained on bilingual corpus in most cases. In this paper, we propose a compact and language-sensitive method for multilingual translation. To maximize parameter sharing, we first present a universal representor to replace both encoder and decoder models. To make the representor sensitive for specific languages, we further introduce language-sensitive embedding, attention, and discriminator with the ability to enhance model performance. We verify our methods on various translation scenarios, including one-to-many, many-to-many and zero-shot. Extensive experiments demonstrate that our proposed methods remarkably outperform strong standard multilingual translation systems on WMT and IWSLT datasets. Moreover, we find that our model is especially helpful in low-resource and zero-shot translation scenarios.
Anthology ID:
P19-1117
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1213–1223
Language:
URL:
https://aclanthology.org/P19-1117
DOI:
10.18653/v1/P19-1117
Bibkey:
Cite (ACL):
Yining Wang, Long Zhou, Jiajun Zhang, Feifei Zhai, Jingfang Xu, and Chengqing Zong. 2019. A Compact and Language-Sensitive Multilingual Translation Method. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1213–1223, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
A Compact and Language-Sensitive Multilingual Translation Method (Wang et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1117.pdf