@inproceedings{halacsy-etal-2008-parallel,
title = "Parallel Creation of {G}igaword Corpora for Medium Density Languages - an Interim Report",
author = "Hal{\'a}csy, P{\'e}ter and
Kornai, Andr{\'a}s and
N{\'e}meth, P{\'e}ter and
Varga, D{\'a}niel",
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/858_paper.pdf",
abstract = "For increased speed in developing gigaword language resources for medium resource density languages we integrated several FOSS tools in the HUN* toolkit. While the speed and efficiency of the resulting pipeline has surpassed our expectations, our experience in developing LDC-style resource packages for Uzbek and Kurdish makes clear that neither the data collection nor the subsequent processing stages can be fully automated.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="halacsy-etal-2008-parallel">
<titleInfo>
<title>Parallel Creation of Gigaword Corpora for Medium Density Languages - an Interim Report</title>
</titleInfo>
<name type="personal">
<namePart type="given">Péter</namePart>
<namePart type="family">Halácsy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">András</namePart>
<namePart type="family">Kornai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Péter</namePart>
<namePart type="family">Németh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dániel</namePart>
<namePart type="family">Varga</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>For increased speed in developing gigaword language resources for medium resource density languages we integrated several FOSS tools in the HUN* toolkit. While the speed and efficiency of the resulting pipeline has surpassed our expectations, our experience in developing LDC-style resource packages for Uzbek and Kurdish makes clear that neither the data collection nor the subsequent processing stages can be fully automated.</abstract>
<identifier type="citekey">halacsy-etal-2008-parallel</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/858_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Parallel Creation of Gigaword Corpora for Medium Density Languages - an Interim Report
%A Halácsy, Péter
%A Kornai, András
%A Németh, Péter
%A Varga, Dániel
%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 halacsy-etal-2008-parallel
%X For increased speed in developing gigaword language resources for medium resource density languages we integrated several FOSS tools in the HUN* toolkit. While the speed and efficiency of the resulting pipeline has surpassed our expectations, our experience in developing LDC-style resource packages for Uzbek and Kurdish makes clear that neither the data collection nor the subsequent processing stages can be fully automated.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/858_paper.pdf
Markdown (Informal)
[Parallel Creation of Gigaword Corpora for Medium Density Languages - an Interim Report](http://www.lrec-conf.org/proceedings/lrec2008/pdf/858_paper.pdf) (Halácsy et al., LREC 2008)
ACL