Neural Machine Translation via Binary Code Prediction

Yusuke Oda, Philip Arthur, Graham Neubig, Koichiro Yoshino, Satoshi Nakamura


Abstract
In this paper, we propose a new method for calculating the output layer in neural machine translation systems. The method is based on predicting a binary code for each word and can reduce computation time/memory requirements of the output layer to be logarithmic in vocabulary size in the best case. In addition, we also introduce two advanced approaches to improve the robustness of the proposed model: using error-correcting codes and combining softmax and binary codes. Experiments on two English-Japanese bidirectional translation tasks show proposed models achieve BLEU scores that approach the softmax, while reducing memory usage to the order of less than 1/10 and improving decoding speed on CPUs by x5 to x10.
Anthology ID:
P17-1079
Volume:
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2017
Address:
Vancouver, Canada
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
850–860
Language:
URL:
https://aclanthology.org/P17-1079
DOI:
10.18653/v1/P17-1079
Bibkey:
Cite (ACL):
Yusuke Oda, Philip Arthur, Graham Neubig, Koichiro Yoshino, and Satoshi Nakamura. 2017. Neural Machine Translation via Binary Code Prediction. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 850–860, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
Neural Machine Translation via Binary Code Prediction (Oda et al., ACL 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/P17-1079.pdf
Video:
 https://vimeo.com/234955136
Data
ASPEC