@inproceedings{gehring-etal-2017-convolutional,
title = "A Convolutional Encoder Model for Neural Machine Translation",
author = "Gehring, Jonas and
Auli, Michael and
Grangier, David and
Dauphin, Yann",
editor = "Barzilay, Regina and
Kan, Min-Yen",
booktitle = "Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P17-1012",
doi = "10.18653/v1/P17-1012",
pages = "123--135",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gehring-etal-2017-convolutional">
<titleInfo>
<title>A Convolutional Encoder Model for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonas</namePart>
<namePart type="family">Gehring</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Auli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Grangier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yann</namePart>
<namePart type="family">Dauphin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Regina</namePart>
<namePart type="family">Barzilay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">gehring-etal-2017-convolutional</identifier>
<identifier type="doi">10.18653/v1/P17-1012</identifier>
<location>
<url>https://aclanthology.org/P17-1012</url>
</location>
<part>
<date>2017-07</date>
<extent unit="page">
<start>123</start>
<end>135</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Convolutional Encoder Model for Neural Machine Translation
%A Gehring, Jonas
%A Auli, Michael
%A Grangier, David
%A Dauphin, Yann
%Y Barzilay, Regina
%Y Kan, Min-Yen
%S Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2017
%8 July
%I Association for Computational Linguistics
%C Vancouver, Canada
%F gehring-etal-2017-convolutional
%X 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.
%R 10.18653/v1/P17-1012
%U https://aclanthology.org/P17-1012
%U https://doi.org/10.18653/v1/P17-1012
%P 123-135
Markdown (Informal)
[A Convolutional Encoder Model for Neural Machine Translation](https://aclanthology.org/P17-1012) (Gehring et al., ACL 2017)
ACL
- Jonas Gehring, Michael Auli, David Grangier, and Yann Dauphin. 2017. A Convolutional Encoder Model for Neural Machine Translation. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 123–135, Vancouver, Canada. Association for Computational Linguistics.