A Convolutional Encoder Model for Neural Machine Translation

Jonas Gehring, Michael Auli, David Grangier, Yann Dauphin


Abstract
The prevalent approach to neural machine translation relies on bi-directional LSTMs to encode the source sentence. We present a faster and simpler architecture based on a succession of convolutional layers. This allows to encode the source sentence simultaneously compared to recurrent networks for which computation is constrained by temporal dependencies. On WMT’16 English-Romanian translation we achieve competitive accuracy to the state-of-the-art and on WMT’15 English-German we outperform several recently published results. Our models obtain almost the same accuracy as a very deep LSTM setup on WMT’14 English-French translation. We speed up CPU decoding by more than two times at the same or higher accuracy as a strong bi-directional LSTM.
Anthology ID:
P17-1012
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:
123–135
Language:
URL:
https://www.aclweb.org/anthology/P17-1012
DOI:
10.18653/v1/P17-1012
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/P17-1012.pdf
Video:
 https://vimeo.com/234951320