<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pu-etal-2018-integrating">
    <titleInfo>
        <title>Integrating Weakly Supervised Word Sense Disambiguation into Neural Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xiao</namePart>
        <namePart type="family">Pu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nikolaos</namePart>
        <namePart type="family">Pappas</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">James</namePart>
        <namePart type="family">Henderson</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andrei</namePart>
        <namePart type="family">Popescu-Belis</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018</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>This paper demonstrates that word sense disambiguation (WSD) can improve neural machine translation (NMT) by widening the source context considered when modeling the senses of potentially ambiguous words. We first introduce three adaptive clustering algorithms for WSD, based on k-means, Chinese restaurant processes, and random walks, which are then applied to large word contexts represented in a low-rank space and evaluated on SemEval shared-task data. We then learn word vectors jointly with sense vectors defined by our best WSD method, within a state-of-the-art NMT system. We show that the concatenation of these vectors, and the use of a sense selection mechanism based on the weighted average of sense vectors, outperforms several baselines including sense-aware ones. This is demonstrated by translation on five language pairs. The improvements are more than 1 BLEU point over strong NMT baselines, +4% accuracy over all ambiguous nouns and verbs, or +20% when scored manually over several challenging words.</abstract>
    <identifier type="citekey">pu-etal-2018-integrating</identifier>
    <identifier type="doi">10.1162/tacl_a_00242</identifier>
    <location>
        <url>https://aclanthology.org/Q18-1044</url>
    </location>
    <part>
        <date>2018</date>
        <detail type="volume"><number>6</number></detail>
        <extent unit="page">
            <start>635</start>
            <end>649</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Integrating Weakly Supervised Word Sense Disambiguation into Neural Machine Translation
%A Pu, Xiao
%A Pappas, Nikolaos
%A Henderson, James
%A Popescu-Belis, Andrei
%J Transactions of the Association for Computational Linguistics
%D 2018
%V 6
%I MIT Press
%C Cambridge, MA
%F pu-etal-2018-integrating
%X This paper demonstrates that word sense disambiguation (WSD) can improve neural machine translation (NMT) by widening the source context considered when modeling the senses of potentially ambiguous words. We first introduce three adaptive clustering algorithms for WSD, based on k-means, Chinese restaurant processes, and random walks, which are then applied to large word contexts represented in a low-rank space and evaluated on SemEval shared-task data. We then learn word vectors jointly with sense vectors defined by our best WSD method, within a state-of-the-art NMT system. We show that the concatenation of these vectors, and the use of a sense selection mechanism based on the weighted average of sense vectors, outperforms several baselines including sense-aware ones. This is demonstrated by translation on five language pairs. The improvements are more than 1 BLEU point over strong NMT baselines, +4% accuracy over all ambiguous nouns and verbs, or +20% when scored manually over several challenging words.
%R 10.1162/tacl_a_00242
%U https://aclanthology.org/Q18-1044
%U https://doi.org/10.1162/tacl_a_00242
%P 635-649

Markdown (Informal)

[Integrating Weakly Supervised Word Sense Disambiguation into Neural Machine Translation](https://aclanthology.org/Q18-1044) (Pu et al., TACL 2018)

• Integrating Weakly Supervised Word Sense Disambiguation into Neural Machine Translation (Pu et al., TACL 2018)

ACL

• Xiao Pu, Nikolaos Pappas, James Henderson, and Andrei Popescu-Belis. 2018. Integrating Weakly Supervised Word Sense Disambiguation into Neural Machine Translation. Transactions of the Association for Computational Linguistics, 6:635–649.