@inproceedings{kemps-snijders-etal-2008-isocat,
title = "{ISO}cat: Corralling Data Categories in the Wild",
author = "Kemps-Snijders, Marc and
Windhouwer, Menzo and
Wittenburg, Peter and
Wright, Sue Ellen",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/222_paper.pdf",
abstract = "To achieve true interoperability for valuable linguistic resources different levels of variation need to be addressed. ISO Technical Committee 37, Terminology and other language and content resources, is developing a Data Category Registry. This registry will provide a reusable set of data categories. A new implementation, dubbed ISOcat, of the registry is currently under construction. This paper shortly describes the new data model for data categories that will be introduced in this implementation. It goes on with a sketch of the standardization process. Completed data categories can be reused by the community. This is done by either making a selection of data categories using the ISOcat web interface, or by other tools which interact with the ISOcat system using one of its various Application Programming Interfaces. Linguistic resources that use data categories from the registry should include persistent references, e.g. in the metadata or schemata of the resource, which point back to their origin. These data category references can then be used to determine if two or more resources share common semantics, thus providing a level of interoperability close to the source data and a promising layer for semantic alignment on higher levels.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kemps-snijders-etal-2008-isocat">
<titleInfo>
<title>ISOcat: Corralling Data Categories in the Wild</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="family">Kemps-Snijders</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Menzo</namePart>
<namePart type="family">Windhouwer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Wittenburg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sue</namePart>
<namePart type="given">Ellen</namePart>
<namePart type="family">Wright</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To achieve true interoperability for valuable linguistic resources different levels of variation need to be addressed. ISO Technical Committee 37, Terminology and other language and content resources, is developing a Data Category Registry. This registry will provide a reusable set of data categories. A new implementation, dubbed ISOcat, of the registry is currently under construction. This paper shortly describes the new data model for data categories that will be introduced in this implementation. It goes on with a sketch of the standardization process. Completed data categories can be reused by the community. This is done by either making a selection of data categories using the ISOcat web interface, or by other tools which interact with the ISOcat system using one of its various Application Programming Interfaces. Linguistic resources that use data categories from the registry should include persistent references, e.g. in the metadata or schemata of the resource, which point back to their origin. These data category references can then be used to determine if two or more resources share common semantics, thus providing a level of interoperability close to the source data and a promising layer for semantic alignment on higher levels.</abstract>
<identifier type="citekey">kemps-snijders-etal-2008-isocat</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/222_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ISOcat: Corralling Data Categories in the Wild
%A Kemps-Snijders, Marc
%A Windhouwer, Menzo
%A Wittenburg, Peter
%A Wright, Sue Ellen
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F kemps-snijders-etal-2008-isocat
%X To achieve true interoperability for valuable linguistic resources different levels of variation need to be addressed. ISO Technical Committee 37, Terminology and other language and content resources, is developing a Data Category Registry. This registry will provide a reusable set of data categories. A new implementation, dubbed ISOcat, of the registry is currently under construction. This paper shortly describes the new data model for data categories that will be introduced in this implementation. It goes on with a sketch of the standardization process. Completed data categories can be reused by the community. This is done by either making a selection of data categories using the ISOcat web interface, or by other tools which interact with the ISOcat system using one of its various Application Programming Interfaces. Linguistic resources that use data categories from the registry should include persistent references, e.g. in the metadata or schemata of the resource, which point back to their origin. These data category references can then be used to determine if two or more resources share common semantics, thus providing a level of interoperability close to the source data and a promising layer for semantic alignment on higher levels.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/222_paper.pdf
Markdown (Informal)
[ISOcat: Corralling Data Categories in the Wild](http://www.lrec-conf.org/proceedings/lrec2008/pdf/222_paper.pdf) (Kemps-Snijders et al., LREC 2008)
ACL
- Marc Kemps-Snijders, Menzo Windhouwer, Peter Wittenburg, and Sue Ellen Wright. 2008. ISOcat: Corralling Data Categories in the Wild. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).