Neural Machine Translation with Word Predictions

Rongxiang Weng, Shujian Huang, Zaixiang Zheng, Xinyu Dai, Jiajun Chen


Abstract
In the encoder-decoder architecture for neural machine translation (NMT), the hidden states of the recurrent structures in the encoder and decoder carry the crucial information about the sentence. These vectors are generated by parameters which are updated by back-propagation of translation errors through time. We argue that propagating errors through the end-to-end recurrent structures are not a direct way of control the hidden vectors. In this paper, we propose to use word predictions as a mechanism for direct supervision. More specifically, we require these vectors to be able to predict the vocabulary in target sentence. Our simple mechanism ensures better representations in the encoder and decoder without using any extra data or annotation. It is also helpful in reducing the target side vocabulary and improving the decoding efficiency. Experiments on Chinese-English machine translation task show an average BLEU improvement by 4.53, respectively.
Anthology ID:
D17-1013
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Editors:
Martha Palmer, Rebecca Hwa, Sebastian Riedel
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
136–145
Language:
URL:
https://aclanthology.org/D17-1013
DOI:
10.18653/v1/D17-1013
Bibkey:
Cite (ACL):
Rongxiang Weng, Shujian Huang, Zaixiang Zheng, Xinyu Dai, and Jiajun Chen. 2017. Neural Machine Translation with Word Predictions. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 136–145, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Neural Machine Translation with Word Predictions (Weng et al., EMNLP 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/D17-1013.pdf