TY - GEN
T1 - Triangular architecture for rare language translation
AU - Ren, Shuo
AU - Chen, Wenhu
AU - Liu, Shujie
AU - Li, Mu
AU - Zhou, Ming
AU - Ma, Shuai
N1 - Publisher Copyright:
© 2018 Association for Computational Linguistics
PY - 2018
Y1 - 2018
N2 - 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 a 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.
AB - 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 a 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.
UR - https://www.scopus.com/pages/publications/85063080825
U2 - 10.18653/v1/p18-1006
DO - 10.18653/v1/p18-1006
M3 - 会议稿件
AN - SCOPUS:85063080825
T3 - ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
SP - 56
EP - 65
BT - ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
PB - Association for Computational Linguistics (ACL)
T2 - 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018
Y2 - 15 July 2018 through 20 July 2018
ER -