@inproceedings{spoustova-spousta-2012-high,
title = "A High-Quality Web Corpus of {C}zech",
author = "Spoustov{\'a}, Johanka and
Spousta, Miroslav",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
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/120_Paper.pdf",
pages = "311--315",
abstract = "In our paper, we present main results of the Czech grant project Internet as a Language Corpus, whose aim was to build a corpus of Czech web texts and to develop and publicly release related software tools. Our corpus may not be the largest web corpus of Czech, but it maintains very good language quality due to high portion of human work involved in the corpus development process. We describe the corpus contents (2.65 billions of words divided into three parts -- 450 millions of words from news and magazines articles, 1 billion of words from blogs, diaries and other non-reviewed literary units, 1.1 billion of words from discussions messages), particular steps of the corpus creation (crawling, HTML and boilerplate removal, near duplicates removal, language filtering) and its automatic language annotation (POS tagging, syntactic parsing). We also describe our software tools being released under an open source license, especially a fast linear-time module for removing near-duplicates on a paragraph level.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="spoustova-spousta-2012-high">
<titleInfo>
<title>A High-Quality Web Corpus of Czech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Johanka</namePart>
<namePart type="family">Spoustová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miroslav</namePart>
<namePart type="family">Spousta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</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>
<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">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Asuncion</namePart>
<namePart type="family">Moreno</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>
<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>In our paper, we present main results of the Czech grant project Internet as a Language Corpus, whose aim was to build a corpus of Czech web texts and to develop and publicly release related software tools. Our corpus may not be the largest web corpus of Czech, but it maintains very good language quality due to high portion of human work involved in the corpus development process. We describe the corpus contents (2.65 billions of words divided into three parts – 450 millions of words from news and magazines articles, 1 billion of words from blogs, diaries and other non-reviewed literary units, 1.1 billion of words from discussions messages), particular steps of the corpus creation (crawling, HTML and boilerplate removal, near duplicates removal, language filtering) and its automatic language annotation (POS tagging, syntactic parsing). We also describe our software tools being released under an open source license, especially a fast linear-time module for removing near-duplicates on a paragraph level.</abstract>
<identifier type="citekey">spoustova-spousta-2012-high</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/120_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>311</start>
<end>315</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A High-Quality Web Corpus of Czech
%A Spoustová, Johanka
%A Spousta, Miroslav
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%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 spoustova-spousta-2012-high
%X In our paper, we present main results of the Czech grant project Internet as a Language Corpus, whose aim was to build a corpus of Czech web texts and to develop and publicly release related software tools. Our corpus may not be the largest web corpus of Czech, but it maintains very good language quality due to high portion of human work involved in the corpus development process. We describe the corpus contents (2.65 billions of words divided into three parts – 450 millions of words from news and magazines articles, 1 billion of words from blogs, diaries and other non-reviewed literary units, 1.1 billion of words from discussions messages), particular steps of the corpus creation (crawling, HTML and boilerplate removal, near duplicates removal, language filtering) and its automatic language annotation (POS tagging, syntactic parsing). We also describe our software tools being released under an open source license, especially a fast linear-time module for removing near-duplicates on a paragraph level.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/120_Paper.pdf
%P 311-315
Markdown (Informal)
[A High-Quality Web Corpus of Czech](http://www.lrec-conf.org/proceedings/lrec2012/pdf/120_Paper.pdf) (Spoustová & Spousta, LREC 2012)
ACL
- Johanka Spoustová and Miroslav Spousta. 2012. A High-Quality Web Corpus of Czech. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 311–315, Istanbul, Turkey. European Language Resources Association (ELRA).