@inproceedings{agic-ljubesic-2014-setimes,
title = "The {SET}imes.{HR} Linguistically Annotated Corpus of {C}roatian",
author = "Agi{\'c}, {\v{Z}}eljko and
Ljube{\v{s}}i{\'c}, Nikola",
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/690_Paper.pdf",
pages = "1724--1727",
abstract = "We present SETimes.HR ― the first linguistically annotated corpus of Croatian that is freely available for all purposes. The corpus is built on top of the SETimes parallel corpus of nine Southeast European languages and English. It is manually annotated for lemmas, morphosyntactic tags, named entities and dependency syntax. We couple the corpus with domain-sensitive test sets for Croatian and Serbian to support direct model transfer evaluation between these closely related languages. We build and evaluate statistical models for lemmatization, morphosyntactic tagging, named entity recognition and dependency parsing on top of SETimes.HR and the test sets, providing the state of the art in all the tasks. We make all resources presented in the paper freely available under a very permissive licensing scheme.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="agic-ljubesic-2014-setimes">
<titleInfo>
<title>The SETimes.HR Linguistically Annotated Corpus of Croatian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Željko</namePart>
<namePart type="family">Agić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</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>We present SETimes.HR ― the first linguistically annotated corpus of Croatian that is freely available for all purposes. The corpus is built on top of the SETimes parallel corpus of nine Southeast European languages and English. It is manually annotated for lemmas, morphosyntactic tags, named entities and dependency syntax. We couple the corpus with domain-sensitive test sets for Croatian and Serbian to support direct model transfer evaluation between these closely related languages. We build and evaluate statistical models for lemmatization, morphosyntactic tagging, named entity recognition and dependency parsing on top of SETimes.HR and the test sets, providing the state of the art in all the tasks. We make all resources presented in the paper freely available under a very permissive licensing scheme.</abstract>
<identifier type="citekey">agic-ljubesic-2014-setimes</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/690_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1724</start>
<end>1727</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The SETimes.HR Linguistically Annotated Corpus of Croatian
%A Agić, Željko
%A Ljubešić, Nikola
%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 agic-ljubesic-2014-setimes
%X We present SETimes.HR ― the first linguistically annotated corpus of Croatian that is freely available for all purposes. The corpus is built on top of the SETimes parallel corpus of nine Southeast European languages and English. It is manually annotated for lemmas, morphosyntactic tags, named entities and dependency syntax. We couple the corpus with domain-sensitive test sets for Croatian and Serbian to support direct model transfer evaluation between these closely related languages. We build and evaluate statistical models for lemmatization, morphosyntactic tagging, named entity recognition and dependency parsing on top of SETimes.HR and the test sets, providing the state of the art in all the tasks. We make all resources presented in the paper freely available under a very permissive licensing scheme.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/690_Paper.pdf
%P 1724-1727
Markdown (Informal)
[The SETimes.HR Linguistically Annotated Corpus of Croatian](http://www.lrec-conf.org/proceedings/lrec2014/pdf/690_Paper.pdf) (Agić & Ljubešić, LREC 2014)
ACL