@inproceedings{cohen-etal-2016-supercat,
title = "{S}uper{CAT}: The (New and Improved) Corpus Analysis Toolkit",
author = "Cohen, K. Bretonnel and
Baumgartner Jr., William A. and
Temnikova, Irina",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1442",
pages = "2784--2788",
abstract = "This paper reports SuperCAT, a corpus analysis toolkit. It is a radical extension of SubCAT, the Sublanguage Corpus Analysis Toolkit, from sublanguage analysis to corpus analysis in general. The idea behind SuperCAT is that representative corpora have no tendency towards closure―that is, they tend towards infinity. In contrast, non-representative corpora have a tendency towards closure―roughly, finiteness. SuperCAT focuses on general techniques for the quantitative description of the characteristics of any corpus (or other language sample), particularly concerning the characteristics of lexical distributions. Additionally, SuperCAT features a complete re-engineering of the previous SubCAT architecture.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cohen-etal-2016-supercat">
<titleInfo>
<title>SuperCAT: The (New and Improved) Corpus Analysis Toolkit</title>
</titleInfo>
<name type="personal">
<namePart type="given">K</namePart>
<namePart type="given">Bretonnel</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Baumgartner Jr.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Irina</namePart>
<namePart type="family">Temnikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">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">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper reports SuperCAT, a corpus analysis toolkit. It is a radical extension of SubCAT, the Sublanguage Corpus Analysis Toolkit, from sublanguage analysis to corpus analysis in general. The idea behind SuperCAT is that representative corpora have no tendency towards closure―that is, they tend towards infinity. In contrast, non-representative corpora have a tendency towards closure―roughly, finiteness. SuperCAT focuses on general techniques for the quantitative description of the characteristics of any corpus (or other language sample), particularly concerning the characteristics of lexical distributions. Additionally, SuperCAT features a complete re-engineering of the previous SubCAT architecture.</abstract>
<identifier type="citekey">cohen-etal-2016-supercat</identifier>
<location>
<url>https://aclanthology.org/L16-1442</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>2784</start>
<end>2788</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SuperCAT: The (New and Improved) Corpus Analysis Toolkit
%A Cohen, K. Bretonnel
%A Baumgartner Jr., William A.
%A Temnikova, Irina
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F cohen-etal-2016-supercat
%X This paper reports SuperCAT, a corpus analysis toolkit. It is a radical extension of SubCAT, the Sublanguage Corpus Analysis Toolkit, from sublanguage analysis to corpus analysis in general. The idea behind SuperCAT is that representative corpora have no tendency towards closure―that is, they tend towards infinity. In contrast, non-representative corpora have a tendency towards closure―roughly, finiteness. SuperCAT focuses on general techniques for the quantitative description of the characteristics of any corpus (or other language sample), particularly concerning the characteristics of lexical distributions. Additionally, SuperCAT features a complete re-engineering of the previous SubCAT architecture.
%U https://aclanthology.org/L16-1442
%P 2784-2788
Markdown (Informal)
[SuperCAT: The (New and Improved) Corpus Analysis Toolkit](https://aclanthology.org/L16-1442) (Cohen et al., LREC 2016)
ACL
- K. Bretonnel Cohen, William A. Baumgartner Jr., and Irina Temnikova. 2016. SuperCAT: The (New and Improved) Corpus Analysis Toolkit. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 2784–2788, Portorož, Slovenia. European Language Resources Association (ELRA).