@inproceedings{rieser-lemon-2008-automatic,
title = "Automatic Learning and Evaluation of User-Centered Objective Functions for Dialogue System Optimisation",
author = "Rieser, Verena and
Lemon, Oliver",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/592_paper.pdf",
abstract = "The ultimate goal when building dialogue systems is to satisfy the needs of real users, but quality assurance for dialogue strategies is a non-trivial problem. The applied evaluation metrics and resulting design principles are often obscure, emerge by trial-and-error, and are highly context dependent. This paper introduces data-driven methods for obtaining reliable objective functions for system design. In particular, we test whether an objective function obtained from Wizard-of-Oz (WOZ) data is a valid estimate of real users preferences. We test this in a test-retest comparison between the model obtained from the WOZ study and the models obtained when testing with real users. We can show that, despite a low fit to the initial data, the objective function obtained from WOZ data makes accurate predictions for automatic dialogue evaluation, and, when automatically optimising a policy using these predictions, the improvement over a strategy simply mimicking the data becomes clear from an error analysis.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rieser-lemon-2008-automatic">
<titleInfo>
<title>Automatic Learning and Evaluation of User-Centered Objective Functions for Dialogue System Optimisation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Verena</namePart>
<namePart type="family">Rieser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oliver</namePart>
<namePart type="family">Lemon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The ultimate goal when building dialogue systems is to satisfy the needs of real users, but quality assurance for dialogue strategies is a non-trivial problem. The applied evaluation metrics and resulting design principles are often obscure, emerge by trial-and-error, and are highly context dependent. This paper introduces data-driven methods for obtaining reliable objective functions for system design. In particular, we test whether an objective function obtained from Wizard-of-Oz (WOZ) data is a valid estimate of real users preferences. We test this in a test-retest comparison between the model obtained from the WOZ study and the models obtained when testing with real users. We can show that, despite a low fit to the initial data, the objective function obtained from WOZ data makes accurate predictions for automatic dialogue evaluation, and, when automatically optimising a policy using these predictions, the improvement over a strategy simply mimicking the data becomes clear from an error analysis.</abstract>
<identifier type="citekey">rieser-lemon-2008-automatic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/592_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Learning and Evaluation of User-Centered Objective Functions for Dialogue System Optimisation
%A Rieser, Verena
%A Lemon, Oliver
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F rieser-lemon-2008-automatic
%X The ultimate goal when building dialogue systems is to satisfy the needs of real users, but quality assurance for dialogue strategies is a non-trivial problem. The applied evaluation metrics and resulting design principles are often obscure, emerge by trial-and-error, and are highly context dependent. This paper introduces data-driven methods for obtaining reliable objective functions for system design. In particular, we test whether an objective function obtained from Wizard-of-Oz (WOZ) data is a valid estimate of real users preferences. We test this in a test-retest comparison between the model obtained from the WOZ study and the models obtained when testing with real users. We can show that, despite a low fit to the initial data, the objective function obtained from WOZ data makes accurate predictions for automatic dialogue evaluation, and, when automatically optimising a policy using these predictions, the improvement over a strategy simply mimicking the data becomes clear from an error analysis.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/592_paper.pdf
Markdown (Informal)
[Automatic Learning and Evaluation of User-Centered Objective Functions for Dialogue System Optimisation](http://www.lrec-conf.org/proceedings/lrec2008/pdf/592_paper.pdf) (Rieser & Lemon, LREC 2008)
ACL