@inproceedings{heid-etal-2010-corpus,
title = "A Corpus Representation Format for Linguistic Web Services: The {D}-{SPIN} Text Corpus Format and its Relationship with {ISO} Standards",
author = "Heid, Ulrich and
Schmid, Helmut and
Eckart, Kerstin and
Hinrichs, Erhard",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/503_Paper.pdf",
abstract = "In the framework of the preparation of linguistic web services for corpus processing, the need for a representation format was felt, which supports interoperability between different web services in a corpus processing pipeline, but also provides a well-defined interface to both, legacy tools and their data formats and upcoming international standards. We present the D-SPIN text corpus format, TCF, which was designed for this purpose. It is a stand-off XML format, inspired by the philosophy of the emerging standards LAF (Linguistic Annotation Framework) and its ``instances'' MAF for morpho-syntactic annotation and SynAF for syntactic annotation. Tools for the exchange with existing (best practice) formats are available, and a converter from MAF to TCF is being tested in spring 2010. We describe the usage scenario where TCF is embedded and the properties and architecture of TCF. We also give examples of TCF encoded data and describe the aspects of syntactic and semantic interoperability already addressed.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="heid-etal-2010-corpus">
<titleInfo>
<title>A Corpus Representation Format for Linguistic Web Services: The D-SPIN Text Corpus Format and its Relationship with ISO Standards</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ulrich</namePart>
<namePart type="family">Heid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helmut</namePart>
<namePart type="family">Schmid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kerstin</namePart>
<namePart type="family">Eckart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erhard</namePart>
<namePart type="family">Hinrichs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">Mike</namePart>
<namePart type="family">Rosner</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">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the framework of the preparation of linguistic web services for corpus processing, the need for a representation format was felt, which supports interoperability between different web services in a corpus processing pipeline, but also provides a well-defined interface to both, legacy tools and their data formats and upcoming international standards. We present the D-SPIN text corpus format, TCF, which was designed for this purpose. It is a stand-off XML format, inspired by the philosophy of the emerging standards LAF (Linguistic Annotation Framework) and its “instances” MAF for morpho-syntactic annotation and SynAF for syntactic annotation. Tools for the exchange with existing (best practice) formats are available, and a converter from MAF to TCF is being tested in spring 2010. We describe the usage scenario where TCF is embedded and the properties and architecture of TCF. We also give examples of TCF encoded data and describe the aspects of syntactic and semantic interoperability already addressed.</abstract>
<identifier type="citekey">heid-etal-2010-corpus</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/503_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Corpus Representation Format for Linguistic Web Services: The D-SPIN Text Corpus Format and its Relationship with ISO Standards
%A Heid, Ulrich
%A Schmid, Helmut
%A Eckart, Kerstin
%A Hinrichs, Erhard
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F heid-etal-2010-corpus
%X In the framework of the preparation of linguistic web services for corpus processing, the need for a representation format was felt, which supports interoperability between different web services in a corpus processing pipeline, but also provides a well-defined interface to both, legacy tools and their data formats and upcoming international standards. We present the D-SPIN text corpus format, TCF, which was designed for this purpose. It is a stand-off XML format, inspired by the philosophy of the emerging standards LAF (Linguistic Annotation Framework) and its “instances” MAF for morpho-syntactic annotation and SynAF for syntactic annotation. Tools for the exchange with existing (best practice) formats are available, and a converter from MAF to TCF is being tested in spring 2010. We describe the usage scenario where TCF is embedded and the properties and architecture of TCF. We also give examples of TCF encoded data and describe the aspects of syntactic and semantic interoperability already addressed.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/503_Paper.pdf
Markdown (Informal)
[A Corpus Representation Format for Linguistic Web Services: The D-SPIN Text Corpus Format and its Relationship with ISO Standards](http://www.lrec-conf.org/proceedings/lrec2010/pdf/503_Paper.pdf) (Heid et al., LREC 2010)
ACL