A Convolutional Encoder Model for Neural Machine TranslationDownload PDF

29 Mar 2024 (modified: 22 Oct 2023)Submitted to ICLR 2017Readers: Everyone
Abstract: 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.
TL;DR: Investigate encoder models for translation and demonstrate that convolutions can outperform LSTMs as encoders.
Conflicts: fb.com
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 2 code implementations](https://www.catalyzex.com/paper/arxiv:1611.02344/code)
18 Replies

Loading