@inproceedings{hladek-etal-2014-slovak,
title = "The {S}lovak Categorized News Corpus",
author = "Hladek, Daniel and
Stas, Jan and
Juhar, Jozef",
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/656_Paper.pdf",
pages = "1705--1708",
abstract = "The presented corpus aims to be the first attempt to create a representative sample of the contemporary Slovak language from various domains with easy searching and automated processing. This first version of the corpus contains words and automatic morphological and named entity annotations and transcriptions of abbreviations and numerals. Integral part of the proposed paper is a word boundary and sentence boundary detection algorithm that utilizes characteristic features of the language.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hladek-etal-2014-slovak">
<titleInfo>
<title>The Slovak Categorized News Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Hladek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Stas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jozef</namePart>
<namePart type="family">Juhar</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 presented corpus aims to be the first attempt to create a representative sample of the contemporary Slovak language from various domains with easy searching and automated processing. This first version of the corpus contains words and automatic morphological and named entity annotations and transcriptions of abbreviations and numerals. Integral part of the proposed paper is a word boundary and sentence boundary detection algorithm that utilizes characteristic features of the language.</abstract>
<identifier type="citekey">hladek-etal-2014-slovak</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/656_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1705</start>
<end>1708</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Slovak Categorized News Corpus
%A Hladek, Daniel
%A Stas, Jan
%A Juhar, Jozef
%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 hladek-etal-2014-slovak
%X The presented corpus aims to be the first attempt to create a representative sample of the contemporary Slovak language from various domains with easy searching and automated processing. This first version of the corpus contains words and automatic morphological and named entity annotations and transcriptions of abbreviations and numerals. Integral part of the proposed paper is a word boundary and sentence boundary detection algorithm that utilizes characteristic features of the language.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/656_Paper.pdf
%P 1705-1708
Markdown (Informal)
[The Slovak Categorized News Corpus](http://www.lrec-conf.org/proceedings/lrec2014/pdf/656_Paper.pdf) (Hladek et al., LREC 2014)
ACL
- Daniel Hladek, Jan Stas, and Jozef Juhar. 2014. The Slovak Categorized News Corpus. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 1705–1708, Reykjavik, Iceland. European Language Resources Association (ELRA).