Contrastive Learning for Many-to-many Multilingual Neural Machine Translation

Xiao Pan, Mingxuan Wang, Liwei Wu, Lei Li


Abstract
Existing multilingual machine translation approaches mainly focus on English-centric directions, while the non-English directions still lag behind. In this work, we aim to build a many-to-many translation system with an emphasis on the quality of non-English language directions. Our intuition is based on the hypothesis that a universal cross-language representation leads to better multilingual translation performance. To this end, we propose mRASP2, a training method to obtain a single unified multilingual translation model. mRASP2 is empowered by two techniques: a) a contrastive learning scheme to close the gap among representations of different languages, and b) data augmentation on both multiple parallel and monolingual data to further align token representations. For English-centric directions, mRASP2 achieves competitive or even better performance than a strong pre-trained model mBART on tens of WMT benchmarks. For non-English directions, mRASP2 achieves an improvement of average 10+ BLEU compared with the multilingual baseline
Anthology ID:
2021.acl-long.21
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:
244–258
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2021.acl-long.21/
DOI:
10.18653/v1/2021.acl-long.21
Bibkey:
Cite (ACL):
Xiao Pan, Mingxuan Wang, Liwei Wu, and Lei Li. 2021. Contrastive Learning for Many-to-many Multilingual 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 244–258, Online. Association for Computational Linguistics.
Cite (Informal):
Contrastive Learning for Many-to-many Multilingual Neural Machine Translation (Pan et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2021.acl-long.21.pdf
Video:
 https://preview.aclanthology.org/build-pipeline-with-new-library/2021.acl-long.21.mp4
Code
 PANXiao1994/mCOLT +  additional community code
Data
OPUS-100