@inproceedings{sharoff-2006-uniform,
title = "A Uniform Interface to Large-Scale Linguistic Resources",
author = "Sharoff, Serge",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/184_pdf.pdf",
abstract = "In the paper we address two practical problems concerning the use of corpora in translation studies. The first stems from the limited resources available for targeted languages and genres within languages, whereas translation researchers and students need: sufficiently large modern corpora, either reflecting general language or specific to a problem domain. The second problem concerns the lackof a uniform interface for accessing the resources, even when the yexist. We deal with the first problem by developing a framework for semi-automatic acquisition of large corpora from the Internet for the languages relevant for our research and training needs. We outline the methodology used and discuss the composition of Internet-derived corpora. We deal with the second problem by developing a uniform interface to our corpora. In addition to standard options for choosingcorpora and sorting concordance lines, the interface can compute the list of collocations and filter the results according touser-specified patterns in order to detect language-specific syntacticstructures.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sharoff-2006-uniform">
<titleInfo>
<title>A Uniform Interface to Large-Scale Linguistic Resources</title>
</titleInfo>
<name type="personal">
<namePart type="given">Serge</namePart>
<namePart type="family">Sharoff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">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">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the paper we address two practical problems concerning the use of corpora in translation studies. The first stems from the limited resources available for targeted languages and genres within languages, whereas translation researchers and students need: sufficiently large modern corpora, either reflecting general language or specific to a problem domain. The second problem concerns the lackof a uniform interface for accessing the resources, even when the yexist. We deal with the first problem by developing a framework for semi-automatic acquisition of large corpora from the Internet for the languages relevant for our research and training needs. We outline the methodology used and discuss the composition of Internet-derived corpora. We deal with the second problem by developing a uniform interface to our corpora. In addition to standard options for choosingcorpora and sorting concordance lines, the interface can compute the list of collocations and filter the results according touser-specified patterns in order to detect language-specific syntacticstructures.</abstract>
<identifier type="citekey">sharoff-2006-uniform</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/184_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Uniform Interface to Large-Scale Linguistic Resources
%A Sharoff, Serge
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F sharoff-2006-uniform
%X In the paper we address two practical problems concerning the use of corpora in translation studies. The first stems from the limited resources available for targeted languages and genres within languages, whereas translation researchers and students need: sufficiently large modern corpora, either reflecting general language or specific to a problem domain. The second problem concerns the lackof a uniform interface for accessing the resources, even when the yexist. We deal with the first problem by developing a framework for semi-automatic acquisition of large corpora from the Internet for the languages relevant for our research and training needs. We outline the methodology used and discuss the composition of Internet-derived corpora. We deal with the second problem by developing a uniform interface to our corpora. In addition to standard options for choosingcorpora and sorting concordance lines, the interface can compute the list of collocations and filter the results according touser-specified patterns in order to detect language-specific syntacticstructures.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/184_pdf.pdf
Markdown (Informal)
[A Uniform Interface to Large-Scale Linguistic Resources](http://www.lrec-conf.org/proceedings/lrec2006/pdf/184_pdf.pdf) (Sharoff, LREC 2006)
ACL