<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="su-etal-2015-reward">
    <titleInfo>
        <title>Reward Shaping with Recurrent Neural Networks for Speeding up On-Line Policy Learning in Spoken Dialogue Systems</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Pei-Hao</namePart>
        <namePart type="family">Su</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">David</namePart>
        <namePart type="family">Vandyke</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Milica</namePart>
        <namePart type="family">Gašić</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nikola</namePart>
        <namePart type="family">Mrkšić</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tsung-Hsien</namePart>
        <namePart type="family">Wen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Steve</namePart>
        <namePart type="family">Young</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2015-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Alexander</namePart>
            <namePart type="family">Koller</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Gabriel</namePart>
            <namePart type="family">Skantze</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Filip</namePart>
            <namePart type="family">Jurcicek</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Masahiro</namePart>
            <namePart type="family">Araki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Carolyn</namePart>
            <namePart type="given">Penstein</namePart>
            <namePart type="family">Rose</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Prague, Czech Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <identifier type="citekey">su-etal-2015-reward</identifier>
    <identifier type="doi">10.18653/v1/W15-4655</identifier>
    <location>
        <url>https://aclanthology.org/W15-4655</url>
    </location>
    <part>
        <date>2015-09</date>
        <extent unit="page">
            <start>417</start>
            <end>421</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Reward Shaping with Recurrent Neural Networks for Speeding up On-Line Policy Learning in Spoken Dialogue Systems
%A Su, Pei-Hao
%A Vandyke, David
%A Gašić, Milica
%A Mrkšić, Nikola
%A Wen, Tsung-Hsien
%A Young, Steve
%Y Koller, Alexander
%Y Skantze, Gabriel
%Y Jurcicek, Filip
%Y Araki, Masahiro
%Y Rose, Carolyn Penstein
%S Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2015
%8 September
%I Association for Computational Linguistics
%C Prague, Czech Republic
%F su-etal-2015-reward
%R 10.18653/v1/W15-4655
%U https://aclanthology.org/W15-4655
%U https://doi.org/10.18653/v1/W15-4655
%P 417-421

Markdown (Informal)

[Reward Shaping with Recurrent Neural Networks for Speeding up On-Line Policy Learning in Spoken Dialogue Systems](https://aclanthology.org/W15-4655) (Su et al., SIGDIAL 2015)

• Reward Shaping with Recurrent Neural Networks for Speeding up On-Line Policy Learning in Spoken Dialogue Systems (Su et al., SIGDIAL 2015)

ACL

• Pei-Hao Su, David Vandyke, Milica Gašić, Nikola Mrkšić, Tsung-Hsien Wen, and Steve Young. 2015. Reward Shaping with Recurrent Neural Networks for Speeding up On-Line Policy Learning in Spoken Dialogue Systems. In Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 417–421, Prague, Czech Republic. Association for Computational Linguistics.