A Convolutional Encoder Model for Neural Machine Translation

Association for Computational Linguistics 2017 (ACL 2017)

By: Jonas Gehring, Michael Auli, David Grangier, Yann Dauphin


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 EnglishRomanian 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 bidirectional LSTM.