Triangular Architecture for Rare Language Translation
Shuo Ren, Wenhu Chen, Shujie Liu, Mu Li, Ming Zhou, Shuai Ma
Abstract
Neural Machine Translation (NMT) performs poor on the low-resource language pair (X,Z), especially when Z is a rare language. By introducing another rich language Y, we propose a novel triangular training architecture (TA-NMT) to leverage bilingual data (Y,Z) (may be small) and (X,Y) (can be rich) to improve the translation performance of low-resource pairs. In this triangular architecture, Z is taken as the intermediate latent variable, and translation models of Z are jointly optimized with an unified bidirectional EM algorithm under the goal of maximizing the translation likelihood of (X,Y). Empirical results demonstrate that our method significantly improves the translation quality of rare languages on MultiUN and IWSLT2012 datasets, and achieves even better performance combining back-translation methods.- Anthology ID:
- P18-1006
- Volume:
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 56–65
- Language:
- URL:
- https://aclanthology.org/P18-1006
- DOI:
- 10.18653/v1/P18-1006
- Cite (ACL):
- Shuo Ren, Wenhu Chen, Shujie Liu, Mu Li, Ming Zhou, and Shuai Ma. 2018. Triangular Architecture for Rare Language Translation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 56–65, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- Triangular Architecture for Rare Language Translation (Ren et al., ACL 2018)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/P18-1006.pdf