The prevalent approach to neural machine translation relies on bi-directional LSTMs to encode the source sentence. In this paper we present a faster and simpler architecture based on a succession of convolutional layers. This allows to encode the entire 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 we outperform several recently published results on the WMT'15 English-German task. Our models obtain almost the same accuracy as a very deep LSTM setup on WMT'14 English-French translation. Our convolutional encoder speeds up CPU decoding by more than two times at the same or higher accuracy as a strong bi-directional LSTM baseline.
@article{arxiv.1611.02344,
title = {A Convolutional Encoder Model for Neural Machine Translation},
author = {Jonas Gehring and Michael Auli and David Grangier and Yann N. Dauphin},
journal= {arXiv preprint arXiv:1611.02344},
year = {2017}
}