Multilingual Mix: Example Interpolation Improves Multilingual Neural Machine Translation

Yong Cheng, Ankur Bapna, Orhan Firat, Yuan Cao, Pidong Wang, Wolfgang Macherey


Abstract
Multilingual neural machine translation models are trained to maximize the likelihood of a mix of examples drawn from multiple language pairs. The dominant inductive bias applied to these models is a shared vocabulary and a shared set of parameters across languages; the inputs and labels corresponding to examples drawn from different language pairs might still reside in distinct sub-spaces. In this paper, we introduce multilingual crossover encoder-decoder (mXEncDec) to fuse language pairs at an instance level. Our approach interpolates instances from different language pairs into joint ‘crossover examples’ in order to encourage sharing input and output spaces across languages. To ensure better fusion of examples in multilingual settings, we propose several techniques to improve example interpolation across dissimilar languages under heavy data imbalance. Experiments on a large-scale WMT multilingual dataset demonstrate that our approach significantly improves quality on English-to-Many, Many-to-English and zero-shot translation tasks (from +0.5 BLEU up to +5.5 BLEU points). Results on code-switching sets demonstrate the capability of our approach to improve model generalization to out-of-distribution multilingual examples. We also conduct qualitative and quantitative representation comparisons to analyze the advantages of our approach at the representation level.
Anthology ID:
2022.acl-long.282
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4092–4102
Language:
URL:
https://aclanthology.org/2022.acl-long.282
DOI:
10.18653/v1/2022.acl-long.282
Bibkey:
Cite (ACL):
Yong Cheng, Ankur Bapna, Orhan Firat, Yuan Cao, Pidong Wang, and Wolfgang Macherey. 2022. Multilingual Mix: Example Interpolation Improves Multilingual Neural Machine Translation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4092–4102, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Multilingual Mix: Example Interpolation Improves Multilingual Neural Machine Translation (Cheng et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.282.pdf