@inproceedings{larson-etal-2020-data,
title = "Data Query Language and Corpus Tools for Slot-Filling and Intent Classification Data",
author = "Larson, Stefan and
Guldan, Eric and
Leach, Kevin",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.873",
pages = "7060--7068",
abstract = "Typical machine learning approaches to developing task-oriented dialog systems require the collection and management of large amounts of training data, especially for the tasks of intent classification and slot-filling. Managing this data can be cumbersome without dedicated tools to help the dialog system designer understand the nature of the data. This paper presents a toolkit for analyzing slot-filling and intent classification corpora. We present a toolkit that includes (1) a new lightweight and readable data and file format for intent classification and slot-filling corpora, (2) a new query language for searching intent classification and slot-filling corpora, and (3) tools for understanding the structure and makeup for such corpora. We apply our toolkit to several well-known NLU datasets, and demonstrate that our toolkit can be used to uncover interesting and surprising insights. By releasing our toolkit to the research community, we hope to enable others to develop more robust and intelligent slot-filling and intent classification models.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="larson-etal-2020-data">
<titleInfo>
<title>Data Query Language and Corpus Tools for Slot-Filling and Intent Classification Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Larson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Guldan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Leach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</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>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Typical machine learning approaches to developing task-oriented dialog systems require the collection and management of large amounts of training data, especially for the tasks of intent classification and slot-filling. Managing this data can be cumbersome without dedicated tools to help the dialog system designer understand the nature of the data. This paper presents a toolkit for analyzing slot-filling and intent classification corpora. We present a toolkit that includes (1) a new lightweight and readable data and file format for intent classification and slot-filling corpora, (2) a new query language for searching intent classification and slot-filling corpora, and (3) tools for understanding the structure and makeup for such corpora. We apply our toolkit to several well-known NLU datasets, and demonstrate that our toolkit can be used to uncover interesting and surprising insights. By releasing our toolkit to the research community, we hope to enable others to develop more robust and intelligent slot-filling and intent classification models.</abstract>
<identifier type="citekey">larson-etal-2020-data</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.873</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>7060</start>
<end>7068</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Data Query Language and Corpus Tools for Slot-Filling and Intent Classification Data
%A Larson, Stefan
%A Guldan, Eric
%A Leach, Kevin
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F larson-etal-2020-data
%X Typical machine learning approaches to developing task-oriented dialog systems require the collection and management of large amounts of training data, especially for the tasks of intent classification and slot-filling. Managing this data can be cumbersome without dedicated tools to help the dialog system designer understand the nature of the data. This paper presents a toolkit for analyzing slot-filling and intent classification corpora. We present a toolkit that includes (1) a new lightweight and readable data and file format for intent classification and slot-filling corpora, (2) a new query language for searching intent classification and slot-filling corpora, and (3) tools for understanding the structure and makeup for such corpora. We apply our toolkit to several well-known NLU datasets, and demonstrate that our toolkit can be used to uncover interesting and surprising insights. By releasing our toolkit to the research community, we hope to enable others to develop more robust and intelligent slot-filling and intent classification models.
%U https://aclanthology.org/2020.lrec-1.873
%P 7060-7068
Markdown (Informal)
[Data Query Language and Corpus Tools for Slot-Filling and Intent Classification Data](https://aclanthology.org/2020.lrec-1.873) (Larson et al., LREC 2020)
ACL