Dynamic Past and Future for Neural Machine Translation

Zaixiang Zheng, Shujian Huang, Zhaopeng Tu, Xin-Yu Dai, Jiajun Chen


Abstract
Previous studies have shown that neural machine translation (NMT) models can benefit from explicitly modeling translated () and untranslated () source contents as recurrent states (CITATION). However, this less interpretable recurrent process hinders its power to model the dynamic updating of and contents during decoding. In this paper, we propose to model the dynamic principles by explicitly separating source words into groups of translated and untranslated contents through parts-to-wholes assignment. The assignment is learned through a novel variant of routing-by-agreement mechanism (CITATION), namely Guided Dynamic Routing, where the translating status at each decoding step guides the routing process to assign each source word to its associated group (i.e., translated or untranslated content) represented by a capsule, enabling translation to be made from holistic context. Experiments show that our approach achieves substantial improvements over both Rnmt and Transformer by producing more adequate translations. Extensive analysis demonstrates that our method is highly interpretable, which is able to recognize the translated and untranslated contents as expected.
Anthology ID:
D19-1086
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:
931–941
Language:
URL:
https://aclanthology.org/D19-1086
DOI:
10.18653/v1/D19-1086
Bibkey:
Cite (ACL):
Zaixiang Zheng, Shujian Huang, Zhaopeng Tu, Xin-Yu Dai, and Jiajun Chen. 2019. Dynamic Past and Future for Neural Machine Translation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 931–941, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Dynamic Past and Future for Neural Machine Translation (Zheng et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/D19-1086.pdf
Attachment:
 D19-1086.Attachment.pdf
Code
 zhengzx-nlp/dynamic-nmt