<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jin-etal-2020-discrete">
    <titleInfo>
        <title>Discrete Latent Variable Representations for Low-Resource Text Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shuning</namePart>
        <namePart type="family">Jin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sam</namePart>
        <namePart type="family">Wiseman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Karl</namePart>
        <namePart type="family">Stratos</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Karen</namePart>
        <namePart type="family">Livescu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Dan</namePart>
            <namePart type="family">Jurafsky</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Chai</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Natalie</namePart>
            <namePart type="family">Schluter</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joel</namePart>
            <namePart type="family">Tetreault</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>While much work on deep latent variable models of text uses continuous latent variables, discrete latent variables are interesting because they are more interpretable and typically more space efficient. We consider several approaches to learning discrete latent variable models for text in the case where exact marginalization over these variables is intractable. We compare the performance of the learned representations as features for low-resource document and sentence classification. Our best models outperform the previous best reported results with continuous representations in these low-resource settings, while learning significantly more compressed representations. Interestingly, we find that an amortized variant of Hard EM performs particularly well in the lowest-resource regimes.</abstract>
    <identifier type="citekey">jin-etal-2020-discrete</identifier>
    <identifier type="doi">10.18653/v1/2020.acl-main.437</identifier>
    <location>
        <url>https://aclanthology.org/2020.acl-main.437</url>
    </location>
    <part>
        <date>2020-07</date>
        <extent unit="page">
            <start>4831</start>
            <end>4842</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Discrete Latent Variable Representations for Low-Resource Text Classification
%A Jin, Shuning
%A Wiseman, Sam
%A Stratos, Karl
%A Livescu, Karen
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F jin-etal-2020-discrete
%X While much work on deep latent variable models of text uses continuous latent variables, discrete latent variables are interesting because they are more interpretable and typically more space efficient. We consider several approaches to learning discrete latent variable models for text in the case where exact marginalization over these variables is intractable. We compare the performance of the learned representations as features for low-resource document and sentence classification. Our best models outperform the previous best reported results with continuous representations in these low-resource settings, while learning significantly more compressed representations. Interestingly, we find that an amortized variant of Hard EM performs particularly well in the lowest-resource regimes.
%R 10.18653/v1/2020.acl-main.437
%U https://aclanthology.org/2020.acl-main.437
%U https://doi.org/10.18653/v1/2020.acl-main.437
%P 4831-4842

Markdown (Informal)

[Discrete Latent Variable Representations for Low-Resource Text Classification](https://aclanthology.org/2020.acl-main.437) (Jin et al., ACL 2020)

• Discrete Latent Variable Representations for Low-Resource Text Classification (Jin et al., ACL 2020)

ACL

• Shuning Jin, Sam Wiseman, Karl Stratos, and Karen Livescu. 2020. Discrete Latent Variable Representations for Low-Resource Text Classification. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4831–4842, Online. Association for Computational Linguistics.