<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tu-etal-2017-context">
    <titleInfo>
        <title>Context Gates for Neural Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zhaopeng</namePart>
        <namePart type="family">Tu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhengdong</namePart>
        <namePart type="family">Lu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaohua</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hang</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>In neural machine translation (NMT), generation of a target word depends on both source and target contexts. We find that source contexts have a direct impact on the adequacy of a translation while target contexts affect the fluency. Intuitively, generation of a content word should rely more on the source context and generation of a functional word should rely more on the target context. Due to the lack of effective control over the influence from source and target contexts, conventional NMT tends to yield fluent but inadequate translations. To address this problem, we propose context gates which dynamically control the ratios at which source and target contexts contribute to the generation of target words. In this way, we can enhance both the adequacy and fluency of NMT with more careful control of the information flow from contexts. Experiments show that our approach significantly improves upon a standard attention-based NMT system by +2.3 BLEU points.</abstract>
    <identifier type="citekey">tu-etal-2017-context</identifier>
    <identifier type="doi">10.1162/tacl_a_00048</identifier>
    <location>
        <url>https://aclanthology.org/Q17-1007</url>
    </location>
    <part>
        <date>2017</date>
        <detail type="volume"><number>5</number></detail>
        <extent unit="page">
            <start>87</start>
            <end>99</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Context Gates for Neural Machine Translation
%A Tu, Zhaopeng
%A Liu, Yang
%A Lu, Zhengdong
%A Liu, Xiaohua
%A Li, Hang
%J Transactions of the Association for Computational Linguistics
%D 2017
%V 5
%I MIT Press
%C Cambridge, MA
%F tu-etal-2017-context
%X In neural machine translation (NMT), generation of a target word depends on both source and target contexts. We find that source contexts have a direct impact on the adequacy of a translation while target contexts affect the fluency. Intuitively, generation of a content word should rely more on the source context and generation of a functional word should rely more on the target context. Due to the lack of effective control over the influence from source and target contexts, conventional NMT tends to yield fluent but inadequate translations. To address this problem, we propose context gates which dynamically control the ratios at which source and target contexts contribute to the generation of target words. In this way, we can enhance both the adequacy and fluency of NMT with more careful control of the information flow from contexts. Experiments show that our approach significantly improves upon a standard attention-based NMT system by +2.3 BLEU points.
%R 10.1162/tacl_a_00048
%U https://aclanthology.org/Q17-1007
%U https://doi.org/10.1162/tacl_a_00048
%P 87-99

Markdown (Informal)

[Context Gates for Neural Machine Translation](https://aclanthology.org/Q17-1007) (Tu et al., TACL 2017)

• Context Gates for Neural Machine Translation (Tu et al., TACL 2017)

ACL

• Zhaopeng Tu, Yang Liu, Zhengdong Lu, Xiaohua Liu, and Hang Li. 2017. Context Gates for Neural Machine Translation. Transactions of the Association for Computational Linguistics, 5:87–99.