@inproceedings{malaviya-etal-2018-sparse,
title = "Sparse and Constrained Attention for Neural Machine Translation",
author = "Malaviya, Chaitanya and
Ferreira, Pedro and
Martins, Andr{\'e} F. T.",
editor = "Gurevych, Iryna and
Miyao, Yusuke",
booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P18-2059",
doi = "10.18653/v1/P18-2059",
pages = "370--376",
abstract = "In neural machine translation, words are sometimes dropped from the source or generated repeatedly in the translation. We explore novel strategies to address the coverage problem that change only the attention transformation. Our approach allocates fertilities to source words, used to bound the attention each word can receive. We experiment with various sparse and constrained attention transformations and propose a new one, constrained sparsemax, shown to be differentiable and sparse. Empirical evaluation is provided in three languages pairs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="malaviya-etal-2018-sparse">
<titleInfo>
<title>Sparse and Constrained Attention for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chaitanya</namePart>
<namePart type="family">Malaviya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="family">Ferreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="given">F</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Miyao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In neural machine translation, words are sometimes dropped from the source or generated repeatedly in the translation. We explore novel strategies to address the coverage problem that change only the attention transformation. Our approach allocates fertilities to source words, used to bound the attention each word can receive. We experiment with various sparse and constrained attention transformations and propose a new one, constrained sparsemax, shown to be differentiable and sparse. Empirical evaluation is provided in three languages pairs.</abstract>
<identifier type="citekey">malaviya-etal-2018-sparse</identifier>
<identifier type="doi">10.18653/v1/P18-2059</identifier>
<location>
<url>https://aclanthology.org/P18-2059</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>370</start>
<end>376</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sparse and Constrained Attention for Neural Machine Translation
%A Malaviya, Chaitanya
%A Ferreira, Pedro
%A Martins, André F. T.
%Y Gurevych, Iryna
%Y Miyao, Yusuke
%S Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F malaviya-etal-2018-sparse
%X In neural machine translation, words are sometimes dropped from the source or generated repeatedly in the translation. We explore novel strategies to address the coverage problem that change only the attention transformation. Our approach allocates fertilities to source words, used to bound the attention each word can receive. We experiment with various sparse and constrained attention transformations and propose a new one, constrained sparsemax, shown to be differentiable and sparse. Empirical evaluation is provided in three languages pairs.
%R 10.18653/v1/P18-2059
%U https://aclanthology.org/P18-2059
%U https://doi.org/10.18653/v1/P18-2059
%P 370-376
Markdown (Informal)
[Sparse and Constrained Attention for Neural Machine Translation](https://aclanthology.org/P18-2059) (Malaviya et al., ACL 2018)
ACL
- Chaitanya Malaviya, Pedro Ferreira, and André F. T. Martins. 2018. Sparse and Constrained Attention for Neural Machine Translation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 370–376, Melbourne, Australia. Association for Computational Linguistics.