<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="balazs-matsuo-2019-gating">
    <titleInfo>
        <title>Gating Mechanisms for Combining Character and Word-level Word Representations: an Empirical Study</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jorge</namePart>
        <namePart type="family">Balazs</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yutaka</namePart>
        <namePart type="family">Matsuo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Sudipta</namePart>
            <namePart type="family">Kar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Farah</namePart>
            <namePart type="family">Nadeem</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Laura</namePart>
            <namePart type="family">Burdick</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Greg</namePart>
            <namePart type="family">Durrett</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Na-Rae</namePart>
            <namePart type="family">Han</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Minneapolis, Minnesota</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In this paper we study how different ways of combining character and word-level representations affect the quality of both final word and sentence representations. We provide strong empirical evidence that modeling characters improves the learned representations at the word and sentence levels, and that doing so is particularly useful when representing less frequent words. We further show that a feature-wise sigmoid gating mechanism is a robust method for creating representations that encode semantic similarity, as it performed reasonably well in several word similarity datasets. Finally, our findings suggest that properly capturing semantic similarity at the word level does not consistently yield improved performance in downstream sentence-level tasks.</abstract>
    <identifier type="citekey">balazs-matsuo-2019-gating</identifier>
    <identifier type="doi">10.18653/v1/N19-3016</identifier>
    <location>
        <url>https://aclanthology.org/N19-3016</url>
    </location>
    <part>
        <date>2019-06</date>
        <extent unit="page">
            <start>110</start>
            <end>124</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Gating Mechanisms for Combining Character and Word-level Word Representations: an Empirical Study
%A Balazs, Jorge
%A Matsuo, Yutaka
%Y Kar, Sudipta
%Y Nadeem, Farah
%Y Burdick, Laura
%Y Durrett, Greg
%Y Han, Na-Rae
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F balazs-matsuo-2019-gating
%X In this paper we study how different ways of combining character and word-level representations affect the quality of both final word and sentence representations. We provide strong empirical evidence that modeling characters improves the learned representations at the word and sentence levels, and that doing so is particularly useful when representing less frequent words. We further show that a feature-wise sigmoid gating mechanism is a robust method for creating representations that encode semantic similarity, as it performed reasonably well in several word similarity datasets. Finally, our findings suggest that properly capturing semantic similarity at the word level does not consistently yield improved performance in downstream sentence-level tasks.
%R 10.18653/v1/N19-3016
%U https://aclanthology.org/N19-3016
%U https://doi.org/10.18653/v1/N19-3016
%P 110-124

Markdown (Informal)

[Gating Mechanisms for Combining Character and Word-level Word Representations: an Empirical Study](https://aclanthology.org/N19-3016) (Balazs & Matsuo, NAACL 2019)

• Gating Mechanisms for Combining Character and Word-level Word Representations: an Empirical Study (Balazs & Matsuo, NAACL 2019)

ACL

• Jorge Balazs and Yutaka Matsuo. 2019. Gating Mechanisms for Combining Character and Word-level Word Representations: an Empirical Study. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop, pages 110–124, Minneapolis, Minnesota. Association for Computational Linguistics.