@inproceedings{kren-etal-2016-syn2015,
title = "{SYN}2015: Representative Corpus of Contemporary Written {C}zech",
author = "K{\v{r}}en, Michal and
Cvr{\v{c}}ek, V{\'a}clav and
{\v{C}}apka, Tom{\'a}{\v{s}} and
{\v{C}}erm{\'a}kov{\'a}, Anna and
Hn{\'a}tkov{\'a}, Milena and
Chlumsk{\'a}, Lucie and
Jel{\'i}nek, Tom{\'a}{\v{s}} and
Kov{\'a}{\v{r}}{\'i}kov{\'a}, Dominika and
Petkevi{\v{c}}, Vladim{\'i}r and
Proch{\'a}zka, Pavel and
Skoumalov{\'a}, Hana and
{\v{S}}krabal, Michal and
Trune{\v{c}}ek, Petr and
Vond{\v{r}}i{\v{c}}ka, Pavel and
Zasina, Adrian Jan",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1400/",
pages = "2522--2528",
abstract = "The paper concentrates on the design, composition and annotation of SYN2015, a new 100-million representative corpus of contemporary written Czech. SYN2015 is a sequel of the representative corpora of the SYN series that can be described as traditional (as opposed to the web-crawled corpora), featuring cleared copyright issues, well-defined composition, reliability of annotation and high-quality text processing. At the same time, SYN2015 is designed as a reflection of the variety of written Czech text production with necessary methodological and technological enhancements that include a detailed bibliographic annotation and text classification based on an updated scheme. The corpus has been produced using a completely rebuilt text processing toolchain called SynKorp. SYN2015 is lemmatized, morphologically and syntactically annotated with state-of-the-art tools. It has been published within the framework of the Czech National Corpus and it is available via the standard corpus query interface KonText at \url{http://kontext.korpus.cz} as well as a dataset in shuffled format."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kren-etal-2016-syn2015">
<titleInfo>
<title>SYN2015: Representative Corpus of Contemporary Written Czech</title>
</titleInfo>
<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">Václav</namePart>
<namePart type="family">Cvrček</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomáš</namePart>
<namePart type="family">Čapka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Čermáková</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Lucie</namePart>
<namePart type="family">Chlumská</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomáš</namePart>
<namePart type="family">Jelínek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dominika</namePart>
<namePart type="family">Kováříková</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vladimír</namePart>
<namePart type="family">Petkevič</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>
<name type="personal">
<namePart type="given">Michal</namePart>
<namePart type="family">Škrabal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petr</namePart>
<namePart type="family">Truneček</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Vondřička</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adrian</namePart>
<namePart type="given">Jan</namePart>
<namePart type="family">Zasina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</namePart>
<namePart type="family">Mazo</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">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The paper concentrates on the design, composition and annotation of SYN2015, a new 100-million representative corpus of contemporary written Czech. SYN2015 is a sequel of the representative corpora of the SYN series that can be described as traditional (as opposed to the web-crawled corpora), featuring cleared copyright issues, well-defined composition, reliability of annotation and high-quality text processing. At the same time, SYN2015 is designed as a reflection of the variety of written Czech text production with necessary methodological and technological enhancements that include a detailed bibliographic annotation and text classification based on an updated scheme. The corpus has been produced using a completely rebuilt text processing toolchain called SynKorp. SYN2015 is lemmatized, morphologically and syntactically annotated with state-of-the-art tools. It has been published within the framework of the Czech National Corpus and it is available via the standard corpus query interface KonText at http://kontext.korpus.cz as well as a dataset in shuffled format.</abstract>
<identifier type="citekey">kren-etal-2016-syn2015</identifier>
<location>
<url>https://aclanthology.org/L16-1400/</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>2522</start>
<end>2528</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SYN2015: Representative Corpus of Contemporary Written Czech
%A Křen, Michal
%A Cvrček, Václav
%A Čapka, Tomáš
%A Čermáková, Anna
%A Hnátková, Milena
%A Chlumská, Lucie
%A Jelínek, Tomáš
%A Kováříková, Dominika
%A Petkevič, Vladimír
%A Procházka, Pavel
%A Skoumalová, Hana
%A Škrabal, Michal
%A Truneček, Petr
%A Vondřička, Pavel
%A Zasina, Adrian Jan
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F kren-etal-2016-syn2015
%X The paper concentrates on the design, composition and annotation of SYN2015, a new 100-million representative corpus of contemporary written Czech. SYN2015 is a sequel of the representative corpora of the SYN series that can be described as traditional (as opposed to the web-crawled corpora), featuring cleared copyright issues, well-defined composition, reliability of annotation and high-quality text processing. At the same time, SYN2015 is designed as a reflection of the variety of written Czech text production with necessary methodological and technological enhancements that include a detailed bibliographic annotation and text classification based on an updated scheme. The corpus has been produced using a completely rebuilt text processing toolchain called SynKorp. SYN2015 is lemmatized, morphologically and syntactically annotated with state-of-the-art tools. It has been published within the framework of the Czech National Corpus and it is available via the standard corpus query interface KonText at http://kontext.korpus.cz as well as a dataset in shuffled format.
%U https://aclanthology.org/L16-1400/
%P 2522-2528
Markdown (Informal)
[SYN2015: Representative Corpus of Contemporary Written Czech](https://aclanthology.org/L16-1400/) (Křen et al., LREC 2016)
ACL
- Michal Křen, Václav Cvrček, Tomáš Čapka, Anna Čermáková, Milena Hnátková, Lucie Chlumská, Tomáš Jelínek, Dominika Kováříková, Vladimír Petkevič, Pavel Procházka, Hana Skoumalová, Michal Škrabal, Petr Truneček, Pavel Vondřička, and Adrian Jan Zasina. 2016. SYN2015: Representative Corpus of Contemporary Written Czech. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 2522–2528, Portorož, Slovenia. European Language Resources Association (ELRA).