@inproceedings{su-etal-2016-line,
title = "On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems",
author = "Su, Pei-Hao and
Ga{\v{s}}i{\'c}, Milica and
Mrk{\v{s}}i{\'c}, Nikola and
Rojas-Barahona, Lina M. and
Ultes, Stefan and
Vandyke, David and
Wen, Tsung-Hsien and
Young, Steve",
editor = "Erk, Katrin and
Smith, Noah A.",
booktitle = "Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2016",
address = "Berlin, Germany",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P16-1230",
doi = "10.18653/v1/P16-1230",
pages = "2431--2441",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="su-etal-2016-line">
<titleInfo>
<title>On-line Active Reward Learning for Policy Optimisation 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">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">Lina</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Rojas-Barahona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Ultes</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">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>2016-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Katrin</namePart>
<namePart type="family">Erk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noah</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Smith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Berlin, Germany</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<identifier type="citekey">su-etal-2016-line</identifier>
<identifier type="doi">10.18653/v1/P16-1230</identifier>
<location>
<url>https://aclanthology.org/P16-1230</url>
</location>
<part>
<date>2016-08</date>
<extent unit="page">
<start>2431</start>
<end>2441</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems
%A Su, Pei-Hao
%A Gašić, Milica
%A Mrkšić, Nikola
%A Rojas-Barahona, Lina M.
%A Ultes, Stefan
%A Vandyke, David
%A Wen, Tsung-Hsien
%A Young, Steve
%Y Erk, Katrin
%Y Smith, Noah A.
%S Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2016
%8 August
%I Association for Computational Linguistics
%C Berlin, Germany
%F su-etal-2016-line
%R 10.18653/v1/P16-1230
%U https://aclanthology.org/P16-1230
%U https://doi.org/10.18653/v1/P16-1230
%P 2431-2441
Markdown (Informal)
[On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems](https://aclanthology.org/P16-1230) (Su et al., ACL 2016)
ACL
- Pei-Hao Su, Milica Gašić, Nikola Mrkšić, Lina M. Rojas-Barahona, Stefan Ultes, David Vandyke, Tsung-Hsien Wen, and Steve Young. 2016. On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2431–2441, Berlin, Germany. Association for Computational Linguistics.