<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kruengkrai-2019-better">
    <titleInfo>
        <title>Better Exploiting Latent Variables in Text Modeling</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Canasai</namePart>
        <namePart type="family">Kruengkrai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Korhonen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Traum</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Màrquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We show that sampling latent variables multiple times at a gradient step helps in improving a variational autoencoder and propose a simple and effective method to better exploit these latent variables through hidden state averaging. Consistent gains in performance on two different datasets, Penn Treebank and Yahoo, indicate the generalizability of our method.</abstract>
    <identifier type="citekey">kruengkrai-2019-better</identifier>
    <identifier type="doi">10.18653/v1/P19-1553</identifier>
    <location>
        <url>https://aclanthology.org/P19-1553</url>
    </location>
    <part>
        <date>2019-07</date>
        <extent unit="page">
            <start>5527</start>
            <end>5532</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Better Exploiting Latent Variables in Text Modeling
%A Kruengkrai, Canasai
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F kruengkrai-2019-better
%X We show that sampling latent variables multiple times at a gradient step helps in improving a variational autoencoder and propose a simple and effective method to better exploit these latent variables through hidden state averaging. Consistent gains in performance on two different datasets, Penn Treebank and Yahoo, indicate the generalizability of our method.
%R 10.18653/v1/P19-1553
%U https://aclanthology.org/P19-1553
%U https://doi.org/10.18653/v1/P19-1553
%P 5527-5532

Markdown (Informal)

[Better Exploiting Latent Variables in Text Modeling](https://aclanthology.org/P19-1553) (Kruengkrai, ACL 2019)

• Better Exploiting Latent Variables in Text Modeling (Kruengkrai, ACL 2019)

ACL

• Canasai Kruengkrai. 2019. Better Exploiting Latent Variables in Text Modeling. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5527–5532, Florence, Italy. Association for Computational Linguistics.