@inproceedings{zseder-etal-2012-rapid,
title = "Rapid creation of large-scale corpora and frequency dictionaries",
author = "Zs{\'e}der, Attila and
Recski, G{\'a}bor and
Varga, D{\'a}niel and
Kornai, Andr{\'a}s",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/783_Paper.pdf",
pages = "1462--1465",
abstract = "We describe, and make public, large-scale language resources and the toolchain used in their creation, for fifteen medium density European languages: Catalan, Czech, Croatian, Danish, Dutch, Finnish, Lithuanian, Norwegian, Polish, Portuguese, Romanian, Serbian, Slovak, Spanish, and Swedish. To make the process uniform across languages, we selected tools that are either language-independent or easily customizable for each language, and reimplemented all stages that were taking too long. To achieve processing times that are insignificant compared to the time data collection (crawling) takes, we reimplemented the standard sentence- and word-level tokenizers and created new boilerplate and near-duplicate detection algorithms. Preliminary experiments with non-European languages indicate that our methods are now applicable not just to our sample, but the entire population of digitally viable languages, with the main limiting factor being the availability of high quality stemmers.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zseder-etal-2012-rapid">
<titleInfo>
<title>Rapid creation of large-scale corpora and frequency dictionaries</title>
</titleInfo>
<name type="personal">
<namePart type="given">Attila</namePart>
<namePart type="family">Zséder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gábor</namePart>
<namePart type="family">Recski</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>
<name type="personal">
<namePart type="given">András</namePart>
<namePart type="family">Kornai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe, and make public, large-scale language resources and the toolchain used in their creation, for fifteen medium density European languages: Catalan, Czech, Croatian, Danish, Dutch, Finnish, Lithuanian, Norwegian, Polish, Portuguese, Romanian, Serbian, Slovak, Spanish, and Swedish. To make the process uniform across languages, we selected tools that are either language-independent or easily customizable for each language, and reimplemented all stages that were taking too long. To achieve processing times that are insignificant compared to the time data collection (crawling) takes, we reimplemented the standard sentence- and word-level tokenizers and created new boilerplate and near-duplicate detection algorithms. Preliminary experiments with non-European languages indicate that our methods are now applicable not just to our sample, but the entire population of digitally viable languages, with the main limiting factor being the availability of high quality stemmers.</abstract>
<identifier type="citekey">zseder-etal-2012-rapid</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/783_Paper.pdf</url>
</location>
<part>
<date>2012-may</date>
<extent unit="page">
<start>1462</start>
<end>1465</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rapid creation of large-scale corpora and frequency dictionaries
%A Zséder, Attila
%A Recski, Gábor
%A Varga, Dániel
%A Kornai, András
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 may
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F zseder-etal-2012-rapid
%X We describe, and make public, large-scale language resources and the toolchain used in their creation, for fifteen medium density European languages: Catalan, Czech, Croatian, Danish, Dutch, Finnish, Lithuanian, Norwegian, Polish, Portuguese, Romanian, Serbian, Slovak, Spanish, and Swedish. To make the process uniform across languages, we selected tools that are either language-independent or easily customizable for each language, and reimplemented all stages that were taking too long. To achieve processing times that are insignificant compared to the time data collection (crawling) takes, we reimplemented the standard sentence- and word-level tokenizers and created new boilerplate and near-duplicate detection algorithms. Preliminary experiments with non-European languages indicate that our methods are now applicable not just to our sample, but the entire population of digitally viable languages, with the main limiting factor being the availability of high quality stemmers.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/783_Paper.pdf
%P 1462-1465
Markdown (Informal)
[Rapid creation of large-scale corpora and frequency dictionaries](http://www.lrec-conf.org/proceedings/lrec2012/pdf/783_Paper.pdf) (Zséder et al., LREC 2012)
ACL