@inproceedings{hnatkova-etal-2014-syn,
title = "The {SYN}-series corpora of written {C}zech",
author = "Hn{\'a}tkov{\'a}, Milena and
K{\v{r}}en, Michal and
Proch{\'a}zka, Pavel and
Skoumalov{\'a}, Hana",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/294_Paper.pdf",
pages = "160--164",
abstract = "The paper overviews the SYN series of synchronic corpora of written Czech compiled within the framework of the Czech National Corpus project. It describes their design and processing with a focus on the annotation, i.e. lemmatization and morphological tagging. The paper also introduces SYN2013PUB, a new 935-million newspaper corpus of Czech published in 2013 as the most recent addition to the SYN series before planned revision of its architecture. SYN2013PUB can be seen as a completion of the series in terms of titles and publication dates of major Czech newspapers that are now covered by complete volumes in comparable proportions. All SYN-series corpora can be characterized as traditional, with emphasis on cleared copyright issues, well-defined composition, reliable metadata and high-quality data processing; their overall size currently exceeds 2.2 billion running words.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hnatkova-etal-2014-syn">
<titleInfo>
<title>The SYN-series corpora of written Czech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Milena</namePart>
<namePart type="family">Hnátková</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michal</namePart>
<namePart type="family">Křen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Procházka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hana</namePart>
<namePart type="family">Skoumalová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The paper overviews the SYN series of synchronic corpora of written Czech compiled within the framework of the Czech National Corpus project. It describes their design and processing with a focus on the annotation, i.e. lemmatization and morphological tagging. The paper also introduces SYN2013PUB, a new 935-million newspaper corpus of Czech published in 2013 as the most recent addition to the SYN series before planned revision of its architecture. SYN2013PUB can be seen as a completion of the series in terms of titles and publication dates of major Czech newspapers that are now covered by complete volumes in comparable proportions. All SYN-series corpora can be characterized as traditional, with emphasis on cleared copyright issues, well-defined composition, reliable metadata and high-quality data processing; their overall size currently exceeds 2.2 billion running words.</abstract>
<identifier type="citekey">hnatkova-etal-2014-syn</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/294_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>160</start>
<end>164</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The SYN-series corpora of written Czech
%A Hnátková, Milena
%A Křen, Michal
%A Procházka, Pavel
%A Skoumalová, Hana
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F hnatkova-etal-2014-syn
%X The paper overviews the SYN series of synchronic corpora of written Czech compiled within the framework of the Czech National Corpus project. It describes their design and processing with a focus on the annotation, i.e. lemmatization and morphological tagging. The paper also introduces SYN2013PUB, a new 935-million newspaper corpus of Czech published in 2013 as the most recent addition to the SYN series before planned revision of its architecture. SYN2013PUB can be seen as a completion of the series in terms of titles and publication dates of major Czech newspapers that are now covered by complete volumes in comparable proportions. All SYN-series corpora can be characterized as traditional, with emphasis on cleared copyright issues, well-defined composition, reliable metadata and high-quality data processing; their overall size currently exceeds 2.2 billion running words.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/294_Paper.pdf
%P 160-164
Markdown (Informal)
[The SYN-series corpora of written Czech](http://www.lrec-conf.org/proceedings/lrec2014/pdf/294_Paper.pdf) (Hnátková et al., LREC 2014)
ACL
- Milena Hnátková, Michal Křen, Pavel Procházka, and Hana Skoumalová. 2014. The SYN-series corpora of written Czech. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 160–164, Reykjavik, Iceland. European Language Resources Association (ELRA).