@inproceedings{webb-etal-2010-evaluating,
title = "Evaluating Human-Machine Conversation for Appropriateness",
author = "Webb, Nick and
Benyon, David and
Hansen, Preben and
Mival, Oil",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/115_Paper.pdf",
abstract = "Evaluation of complex, collaborative dialogue systems is a difficult task. Traditionally, developers have relied upon subjective feedback from the user, and parametrisation over observable metrics. However, both models place some reliance on the notion of a task; that is, the system is helping to user achieve some clearly defined goal, such as book a flight or complete a banking transaction. It is not clear that such metrics are as useful when dealing with a system that has a more complex task, or even no definable task at all, beyond maintain and performing a collaborative dialogue. Working within the EU funded COMPANIONS program, we investigate the use of appropriateness as a measure of conversation quality, the hypothesis being that good companions need to be good conversational partners . We report initial work in the direction of annotating dialogue for indicators of good conversation, including the annotation and comparison of the output of two generations of the same dialogue system.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="webb-etal-2010-evaluating">
<titleInfo>
<title>Evaluating Human-Machine Conversation for Appropriateness</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nick</namePart>
<namePart type="family">Webb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Benyon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preben</namePart>
<namePart type="family">Hansen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oil</namePart>
<namePart type="family">Mival</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">Mike</namePart>
<namePart type="family">Rosner</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">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Evaluation of complex, collaborative dialogue systems is a difficult task. Traditionally, developers have relied upon subjective feedback from the user, and parametrisation over observable metrics. However, both models place some reliance on the notion of a task; that is, the system is helping to user achieve some clearly defined goal, such as book a flight or complete a banking transaction. It is not clear that such metrics are as useful when dealing with a system that has a more complex task, or even no definable task at all, beyond maintain and performing a collaborative dialogue. Working within the EU funded COMPANIONS program, we investigate the use of appropriateness as a measure of conversation quality, the hypothesis being that good companions need to be good conversational partners . We report initial work in the direction of annotating dialogue for indicators of good conversation, including the annotation and comparison of the output of two generations of the same dialogue system.</abstract>
<identifier type="citekey">webb-etal-2010-evaluating</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/115_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Human-Machine Conversation for Appropriateness
%A Webb, Nick
%A Benyon, David
%A Hansen, Preben
%A Mival, Oil
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F webb-etal-2010-evaluating
%X Evaluation of complex, collaborative dialogue systems is a difficult task. Traditionally, developers have relied upon subjective feedback from the user, and parametrisation over observable metrics. However, both models place some reliance on the notion of a task; that is, the system is helping to user achieve some clearly defined goal, such as book a flight or complete a banking transaction. It is not clear that such metrics are as useful when dealing with a system that has a more complex task, or even no definable task at all, beyond maintain and performing a collaborative dialogue. Working within the EU funded COMPANIONS program, we investigate the use of appropriateness as a measure of conversation quality, the hypothesis being that good companions need to be good conversational partners . We report initial work in the direction of annotating dialogue for indicators of good conversation, including the annotation and comparison of the output of two generations of the same dialogue system.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/115_Paper.pdf
Markdown (Informal)
[Evaluating Human-Machine Conversation for Appropriateness](http://www.lrec-conf.org/proceedings/lrec2010/pdf/115_Paper.pdf) (Webb et al., LREC 2010)
ACL
- Nick Webb, David Benyon, Preben Hansen, and Oil Mival. 2010. Evaluating Human-Machine Conversation for Appropriateness. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).