@inproceedings{stefanec-etal-2016-croatian,
title = "{C}roatian Error-Annotated Corpus of Non-Professional Written Language",
author = "{\v{S}}tefanec, Vanja and
Ljube{\v{s}}i{\'c}, Nikola and
Kraljevi{\'c}, Jelena Kuva{\v{c}}",
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/L16-1513",
pages = "3220--3226",
abstract = "In the paper authors present the Croatian corpus of non-professional written language. Consisting of two subcorpora, i.e. the clinical subcorpus, consisting of written texts produced by speakers with various types of language disorders, and the healthy speakers subcorpus, as well as by the levels of its annotation, it offers an opportunity for different lines of research. The authors present the corpus structure, describe the sampling methodology, explain the levels of annotation, and give some very basic statistics. On the basis of data from the corpus, existing language technologies for Croatian are adapted in order to be implemented in a platform facilitating text production to speakers with language disorders. In this respect, several analyses of the corpus data and a basic evaluation of the developed technologies are presented.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stefanec-etal-2016-croatian">
<titleInfo>
<title>Croatian Error-Annotated Corpus of Non-Professional Written Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vanja</namePart>
<namePart type="family">Štefanec</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>
<name type="personal">
<namePart type="given">Jelena</namePart>
<namePart type="given">Kuvač</namePart>
<namePart type="family">Kraljević</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>In the paper authors present the Croatian corpus of non-professional written language. Consisting of two subcorpora, i.e. the clinical subcorpus, consisting of written texts produced by speakers with various types of language disorders, and the healthy speakers subcorpus, as well as by the levels of its annotation, it offers an opportunity for different lines of research. The authors present the corpus structure, describe the sampling methodology, explain the levels of annotation, and give some very basic statistics. On the basis of data from the corpus, existing language technologies for Croatian are adapted in order to be implemented in a platform facilitating text production to speakers with language disorders. In this respect, several analyses of the corpus data and a basic evaluation of the developed technologies are presented.</abstract>
<identifier type="citekey">stefanec-etal-2016-croatian</identifier>
<location>
<url>https://aclanthology.org/L16-1513</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3220</start>
<end>3226</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Croatian Error-Annotated Corpus of Non-Professional Written Language
%A Štefanec, Vanja
%A Ljubešić, Nikola
%A Kraljević, Jelena Kuvač
%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 stefanec-etal-2016-croatian
%X In the paper authors present the Croatian corpus of non-professional written language. Consisting of two subcorpora, i.e. the clinical subcorpus, consisting of written texts produced by speakers with various types of language disorders, and the healthy speakers subcorpus, as well as by the levels of its annotation, it offers an opportunity for different lines of research. The authors present the corpus structure, describe the sampling methodology, explain the levels of annotation, and give some very basic statistics. On the basis of data from the corpus, existing language technologies for Croatian are adapted in order to be implemented in a platform facilitating text production to speakers with language disorders. In this respect, several analyses of the corpus data and a basic evaluation of the developed technologies are presented.
%U https://aclanthology.org/L16-1513
%P 3220-3226
Markdown (Informal)
[Croatian Error-Annotated Corpus of Non-Professional Written Language](https://aclanthology.org/L16-1513) (Štefanec et al., LREC 2016)
ACL