@inproceedings{lee-etal-2018-dialcrowd,
title = "{D}ial{C}rowd: A toolkit for easy dialog system assessment",
author = "Lee, Kyusong and
Zhao, Tiancheng and
Black, Alan W. and
Eskenazi, Maxine",
editor = "Komatani, Kazunori and
Litman, Diane and
Yu, Kai and
Papangelis, Alex and
Cavedon, Lawrence and
Nakano, Mikio",
booktitle = "Proceedings of the 19th Annual {SIG}dial Meeting on Discourse and Dialogue",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-5028",
doi = "10.18653/v1/W18-5028",
pages = "245--248",
abstract = "When creating a dialog system, developers need to test each version to ensure that it is performing correctly. Recently the trend has been to test on large datasets or to ask many users to try out a system. Crowdsourcing has solved the issue of finding users, but it presents new challenges such as how to use a crowdsourcing platform and what type of test is appropriate. DialCrowd has been designed to make system assessment easier and to ensure the quality of the result. This paper describes DialCrowd, what specific needs it fulfills and how it works. It then relates a test of DialCrowd by a group of dialog system developer.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2018-dialcrowd">
<titleInfo>
<title>DialCrowd: A toolkit for easy dialog system assessment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kyusong</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tiancheng</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="given">W</namePart>
<namePart type="family">Black</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maxine</namePart>
<namePart type="family">Eskenazi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kazunori</namePart>
<namePart type="family">Komatani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diane</namePart>
<namePart type="family">Litman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Papangelis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lawrence</namePart>
<namePart type="family">Cavedon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikio</namePart>
<namePart type="family">Nakano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>When creating a dialog system, developers need to test each version to ensure that it is performing correctly. Recently the trend has been to test on large datasets or to ask many users to try out a system. Crowdsourcing has solved the issue of finding users, but it presents new challenges such as how to use a crowdsourcing platform and what type of test is appropriate. DialCrowd has been designed to make system assessment easier and to ensure the quality of the result. This paper describes DialCrowd, what specific needs it fulfills and how it works. It then relates a test of DialCrowd by a group of dialog system developer.</abstract>
<identifier type="citekey">lee-etal-2018-dialcrowd</identifier>
<identifier type="doi">10.18653/v1/W18-5028</identifier>
<location>
<url>https://aclanthology.org/W18-5028</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>245</start>
<end>248</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DialCrowd: A toolkit for easy dialog system assessment
%A Lee, Kyusong
%A Zhao, Tiancheng
%A Black, Alan W.
%A Eskenazi, Maxine
%Y Komatani, Kazunori
%Y Litman, Diane
%Y Yu, Kai
%Y Papangelis, Alex
%Y Cavedon, Lawrence
%Y Nakano, Mikio
%S Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F lee-etal-2018-dialcrowd
%X When creating a dialog system, developers need to test each version to ensure that it is performing correctly. Recently the trend has been to test on large datasets or to ask many users to try out a system. Crowdsourcing has solved the issue of finding users, but it presents new challenges such as how to use a crowdsourcing platform and what type of test is appropriate. DialCrowd has been designed to make system assessment easier and to ensure the quality of the result. This paper describes DialCrowd, what specific needs it fulfills and how it works. It then relates a test of DialCrowd by a group of dialog system developer.
%R 10.18653/v1/W18-5028
%U https://aclanthology.org/W18-5028
%U https://doi.org/10.18653/v1/W18-5028
%P 245-248
Markdown (Informal)
[DialCrowd: A toolkit for easy dialog system assessment](https://aclanthology.org/W18-5028) (Lee et al., SIGDIAL 2018)
ACL
- Kyusong Lee, Tiancheng Zhao, Alan W. Black, and Maxine Eskenazi. 2018. DialCrowd: A toolkit for easy dialog system assessment. In Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue, pages 245–248, Melbourne, Australia. Association for Computational Linguistics.