Multi-agent Learning for Neural Machine Translation

Tianchi Bi, Hao Xiong, Zhongjun He, Hua Wu, Haifeng Wang


Abstract
Conventional Neural Machine Translation (NMT) models benefit from the training with an additional agent, e.g., dual learning, and bidirectional decoding with one agent decod- ing from left to right and the other decoding in the opposite direction. In this paper, we extend the training framework to the multi-agent sce- nario by introducing diverse agents in an in- teractive updating process. At training time, each agent learns advanced knowledge from others, and they work together to improve translation quality. Experimental results on NIST Chinese-English, IWSLT 2014 German- English, WMT 2014 English-German and large-scale Chinese-English translation tasks indicate that our approach achieves absolute improvements over the strong baseline sys- tems and shows competitive performance on all tasks.
Anthology ID:
D19-1079
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
856–865
URL:
https://www.aclweb.org/anthology/D19-1079
DOI:
10.18653/v1/D19-1079
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
https://www.aclweb.org/anthology/D19-1079.pdf