@inproceedings{jwalapuram-2017-evaluating,
title = "Evaluating Dialogs based on {G}rice`s Maxims",
author = "Jwalapuram, Prathyusha",
editor = "Kovatchev, Venelin and
Temnikova, Irina and
Gencheva, Pepa and
Kiprov, Yasen and
Nikolova, Ivelina",
booktitle = "Proceedings of the Student Research Workshop Associated with {RANLP} 2017",
month = sep,
year = "2017",
address = "Varna",
publisher = "INCOMA Ltd.",
url = "https://aclanthology.org/R17-2003/",
doi = "10.26615/issn.1314-9156.2017_003",
pages = "17--24",
abstract = "There is no agreed upon standard for the evaluation of conversational dialog systems, which are well-known to be hard to evaluate due to the difficulty in pinning down metrics that will correspond to human judgements and the subjective nature of human judgment itself. We explored the possibility of using Grice`s Maxims to evaluate effective communication in conversation. We collected some system generated dialogs from popular conversational chatbots across the spectrum and conducted a survey to see how the human judgements based on Gricean maxims correlate, and if such human judgments can be used as an effective evaluation metric for conversational dialog."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jwalapuram-2017-evaluating">
<titleInfo>
<title>Evaluating Dialogs based on Grice‘s Maxims</title>
</titleInfo>
<name type="personal">
<namePart type="given">Prathyusha</namePart>
<namePart type="family">Jwalapuram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Student Research Workshop Associated with RANLP 2017</title>
</titleInfo>
<name type="personal">
<namePart type="given">Venelin</namePart>
<namePart type="family">Kovatchev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Irina</namePart>
<namePart type="family">Temnikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Gencheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yasen</namePart>
<namePart type="family">Kiprov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivelina</namePart>
<namePart type="family">Nikolova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Varna</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>There is no agreed upon standard for the evaluation of conversational dialog systems, which are well-known to be hard to evaluate due to the difficulty in pinning down metrics that will correspond to human judgements and the subjective nature of human judgment itself. We explored the possibility of using Grice‘s Maxims to evaluate effective communication in conversation. We collected some system generated dialogs from popular conversational chatbots across the spectrum and conducted a survey to see how the human judgements based on Gricean maxims correlate, and if such human judgments can be used as an effective evaluation metric for conversational dialog.</abstract>
<identifier type="citekey">jwalapuram-2017-evaluating</identifier>
<identifier type="doi">10.26615/issn.1314-9156.2017_003</identifier>
<location>
<url>https://aclanthology.org/R17-2003/</url>
</location>
<part>
<date>2017-09</date>
<extent unit="page">
<start>17</start>
<end>24</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Dialogs based on Grice‘s Maxims
%A Jwalapuram, Prathyusha
%Y Kovatchev, Venelin
%Y Temnikova, Irina
%Y Gencheva, Pepa
%Y Kiprov, Yasen
%Y Nikolova, Ivelina
%S Proceedings of the Student Research Workshop Associated with RANLP 2017
%D 2017
%8 September
%I INCOMA Ltd.
%C Varna
%F jwalapuram-2017-evaluating
%X There is no agreed upon standard for the evaluation of conversational dialog systems, which are well-known to be hard to evaluate due to the difficulty in pinning down metrics that will correspond to human judgements and the subjective nature of human judgment itself. We explored the possibility of using Grice‘s Maxims to evaluate effective communication in conversation. We collected some system generated dialogs from popular conversational chatbots across the spectrum and conducted a survey to see how the human judgements based on Gricean maxims correlate, and if such human judgments can be used as an effective evaluation metric for conversational dialog.
%R 10.26615/issn.1314-9156.2017_003
%U https://aclanthology.org/R17-2003/
%U https://doi.org/10.26615/issn.1314-9156.2017_003
%P 17-24
Markdown (Informal)
[Evaluating Dialogs based on Grice’s Maxims](https://aclanthology.org/R17-2003/) (Jwalapuram, RANLP 2017)
ACL