<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="feng-etal-2016-improving">
    <titleInfo>
        <title>Improving Attention Modeling with Implicit Distortion and Fertility for Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shi</namePart>
        <namePart type="family">Feng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shujie</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nan</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mu</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ming</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kenny</namePart>
        <namePart type="given">Q</namePart>
        <namePart type="family">Zhu</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>In neural machine translation, the attention mechanism facilitates the translation process by producing a soft alignment between the source sentence and the target sentence. However, without dedicated distortion and fertility models seen in traditional SMT systems, the learned alignment may not be accurate, which can lead to low translation quality. In this paper, we propose two novel models to improve attention-based neural machine translation. We propose a recurrent attention mechanism as an implicit distortion model, and a fertility conditioned decoder as an implicit fertility model. We conduct experiments on large-scale Chinese–English translation tasks. The results show that our models significantly improve both the alignment and translation quality compared to the original attention mechanism and several other variations.</abstract>
    <identifier type="citekey">feng-etal-2016-improving</identifier>
    <location>
        <url>https://aclanthology.org/C16-1290</url>
    </location>
    <part>
        <date>2016-12</date>
        <extent unit="page">
            <start>3082</start>
            <end>3092</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Improving Attention Modeling with Implicit Distortion and Fertility for Machine Translation
%A Feng, Shi
%A Liu, Shujie
%A Yang, Nan
%A Li, Mu
%A Zhou, Ming
%A Zhu, Kenny Q.
%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 feng-etal-2016-improving
%X In neural machine translation, the attention mechanism facilitates the translation process by producing a soft alignment between the source sentence and the target sentence. However, without dedicated distortion and fertility models seen in traditional SMT systems, the learned alignment may not be accurate, which can lead to low translation quality. In this paper, we propose two novel models to improve attention-based neural machine translation. We propose a recurrent attention mechanism as an implicit distortion model, and a fertility conditioned decoder as an implicit fertility model. We conduct experiments on large-scale Chinese–English translation tasks. The results show that our models significantly improve both the alignment and translation quality compared to the original attention mechanism and several other variations.
%U https://aclanthology.org/C16-1290
%P 3082-3092

Markdown (Informal)

[Improving Attention Modeling with Implicit Distortion and Fertility for Machine Translation](https://aclanthology.org/C16-1290) (Feng et al., COLING 2016)

• Improving Attention Modeling with Implicit Distortion and Fertility for Machine Translation (Feng et al., COLING 2016)

ACL

• Shi Feng, Shujie Liu, Nan Yang, Mu Li, Ming Zhou, and Kenny Q. Zhu. 2016. Improving Attention Modeling with Implicit Distortion and Fertility for Machine Translation. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 3082–3092, Osaka, Japan. The COLING 2016 Organizing Committee.