@inproceedings{elbayad-etal-2018-pervasive,
title = "Pervasive Attention: 2{D} Convolutional Neural Networks for Sequence-to-Sequence Prediction",
author = "Elbayad, Maha and
Besacier, Laurent and
Verbeek, Jakob",
editor = "Korhonen, Anna and
Titov, Ivan",
booktitle = "Proceedings of the 22nd Conference on Computational Natural Language Learning",
month = oct,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/K18-1010/",
doi = "10.18653/v1/K18-1010",
pages = "97--107",
abstract = "Current state-of-the-art machine translation systems are based on encoder-decoder architectures, that first encode the input sequence, and then generate an output sequence based on the input encoding. Both are interfaced with an attention mechanism that recombines a fixed encoding of the source tokens based on the decoder state. We propose an alternative approach which instead relies on a single 2D convolutional neural network across both sequences. Each layer of our network re-codes source tokens on the basis of the output sequence produced so far. Attention-like properties are therefore pervasive throughout the network. Our model yields excellent results, outperforming state-of-the-art encoder-decoder systems, while being conceptually simpler and having fewer parameters."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="elbayad-etal-2018-pervasive">
<titleInfo>
<title>Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maha</namePart>
<namePart type="family">Elbayad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurent</namePart>
<namePart type="family">Besacier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jakob</namePart>
<namePart type="family">Verbeek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Conference on Computational Natural Language Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Titov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Current state-of-the-art machine translation systems are based on encoder-decoder architectures, that first encode the input sequence, and then generate an output sequence based on the input encoding. Both are interfaced with an attention mechanism that recombines a fixed encoding of the source tokens based on the decoder state. We propose an alternative approach which instead relies on a single 2D convolutional neural network across both sequences. Each layer of our network re-codes source tokens on the basis of the output sequence produced so far. Attention-like properties are therefore pervasive throughout the network. Our model yields excellent results, outperforming state-of-the-art encoder-decoder systems, while being conceptually simpler and having fewer parameters.</abstract>
<identifier type="citekey">elbayad-etal-2018-pervasive</identifier>
<identifier type="doi">10.18653/v1/K18-1010</identifier>
<location>
<url>https://aclanthology.org/K18-1010/</url>
</location>
<part>
<date>2018-10</date>
<extent unit="page">
<start>97</start>
<end>107</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction
%A Elbayad, Maha
%A Besacier, Laurent
%A Verbeek, Jakob
%Y Korhonen, Anna
%Y Titov, Ivan
%S Proceedings of the 22nd Conference on Computational Natural Language Learning
%D 2018
%8 October
%I Association for Computational Linguistics
%C Brussels, Belgium
%F elbayad-etal-2018-pervasive
%X Current state-of-the-art machine translation systems are based on encoder-decoder architectures, that first encode the input sequence, and then generate an output sequence based on the input encoding. Both are interfaced with an attention mechanism that recombines a fixed encoding of the source tokens based on the decoder state. We propose an alternative approach which instead relies on a single 2D convolutional neural network across both sequences. Each layer of our network re-codes source tokens on the basis of the output sequence produced so far. Attention-like properties are therefore pervasive throughout the network. Our model yields excellent results, outperforming state-of-the-art encoder-decoder systems, while being conceptually simpler and having fewer parameters.
%R 10.18653/v1/K18-1010
%U https://aclanthology.org/K18-1010/
%U https://doi.org/10.18653/v1/K18-1010
%P 97-107
Markdown (Informal)
[Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction](https://aclanthology.org/K18-1010/) (Elbayad et al., CoNLL 2018)
ACL