@inproceedings{liu-etal-2016-neural,
title = "Neural Machine Translation with Supervised Attention",
author = "Liu, Lemao and
Utiyama, Masao and
Finch, Andrew and
Sumita, Eiichiro",
editor = "Matsumoto, Yuji and
Prasad, Rashmi",
booktitle = "Proceedings of {COLING} 2016, the 26th International Conference on Computational Linguistics: Technical Papers",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/C16-1291",
pages = "3093--3102",
abstract = "The attention mechanism is appealing for neural machine translation, since it is able to dynamically encode a source sentence by generating a alignment between a target word and source words. Unfortunately, it has been proved to be worse than conventional alignment models in alignment accuracy. In this paper, we analyze and explain this issue from the point view of reordering, and propose a supervised attention which is learned with guidance from conventional alignment models. Experiments on two Chinese-to-English translation tasks show that the supervised attention mechanism yields better alignments leading to substantial gains over the standard attention based NMT.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2016-neural">
<titleInfo>
<title>Neural Machine Translation with Supervised Attention</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lemao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masao</namePart>
<namePart type="family">Utiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Finch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eiichiro</namePart>
<namePart type="family">Sumita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuji</namePart>
<namePart type="family">Matsumoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rashmi</namePart>
<namePart type="family">Prasad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The attention mechanism is appealing for neural machine translation, since it is able to dynamically encode a source sentence by generating a alignment between a target word and source words. Unfortunately, it has been proved to be worse than conventional alignment models in alignment accuracy. In this paper, we analyze and explain this issue from the point view of reordering, and propose a supervised attention which is learned with guidance from conventional alignment models. Experiments on two Chinese-to-English translation tasks show that the supervised attention mechanism yields better alignments leading to substantial gains over the standard attention based NMT.</abstract>
<identifier type="citekey">liu-etal-2016-neural</identifier>
<location>
<url>https://aclanthology.org/C16-1291</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>3093</start>
<end>3102</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Machine Translation with Supervised Attention
%A Liu, Lemao
%A Utiyama, Masao
%A Finch, Andrew
%A Sumita, Eiichiro
%Y Matsumoto, Yuji
%Y Prasad, Rashmi
%S Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F liu-etal-2016-neural
%X The attention mechanism is appealing for neural machine translation, since it is able to dynamically encode a source sentence by generating a alignment between a target word and source words. Unfortunately, it has been proved to be worse than conventional alignment models in alignment accuracy. In this paper, we analyze and explain this issue from the point view of reordering, and propose a supervised attention which is learned with guidance from conventional alignment models. Experiments on two Chinese-to-English translation tasks show that the supervised attention mechanism yields better alignments leading to substantial gains over the standard attention based NMT.
%U https://aclanthology.org/C16-1291
%P 3093-3102
Markdown (Informal)
[Neural Machine Translation with Supervised Attention](https://aclanthology.org/C16-1291) (Liu et al., COLING 2016)
ACL
- Lemao Liu, Masao Utiyama, Andrew Finch, and Eiichiro Sumita. 2016. Neural Machine Translation with Supervised Attention. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 3093–3102, Osaka, Japan. The COLING 2016 Organizing Committee.