@inproceedings{mititelu-etal-2014-corola,
title = "{C}o{R}o{L}a {---} The Reference Corpus of Contemporary {R}omanian Language",
author = "Mititelu, Verginica Barbu and
Irimia, Elena and
Tufi{\textcommabelow{s}}, Dan",
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/360_Paper.pdf",
pages = "1235--1239",
abstract = "We present the project of creating CoRoLa, a reference corpus of contemporary Romanian (from 1945 onwards). In the international context, the project finds its place among the initiatives of gathering huge collections of texts, of pre-processing and annotating them at several levels, and also of documenting them with metadata (CMDI). Our project is a joined effort of two institutes of the Romanian Academy. We foresee a corpus of more than 500 million word forms, covering all functional styles of the language. Although the vast majority of texts will be in written form, we target about 300 hours of oral texts, too, obligatorily with associated transcripts. Most of the texts will be from books, while the rest will be harvested from newspapers, booklets, technical reports, etc. The pre-processing includes cleaning the data and harmonising the diacritics, sentence splitting and tokenization. Annotation will be done at a morphological level in a first stage, followed by lemmatization, with the possibility of adding syntactic, semantic and discourse annotation in a later stage. A core of CoRoLa is described in the article. The target users of our corpus will be researchers in linguistics and language processing, teachers of Romanian, students.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mititelu-etal-2014-corola">
<titleInfo>
<title>CoRoLa — The Reference Corpus of Contemporary Romanian Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Verginica</namePart>
<namePart type="given">Barbu</namePart>
<namePart type="family">Mititelu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Irimia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Tufi\textcommabelows</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 the project of creating CoRoLa, a reference corpus of contemporary Romanian (from 1945 onwards). In the international context, the project finds its place among the initiatives of gathering huge collections of texts, of pre-processing and annotating them at several levels, and also of documenting them with metadata (CMDI). Our project is a joined effort of two institutes of the Romanian Academy. We foresee a corpus of more than 500 million word forms, covering all functional styles of the language. Although the vast majority of texts will be in written form, we target about 300 hours of oral texts, too, obligatorily with associated transcripts. Most of the texts will be from books, while the rest will be harvested from newspapers, booklets, technical reports, etc. The pre-processing includes cleaning the data and harmonising the diacritics, sentence splitting and tokenization. Annotation will be done at a morphological level in a first stage, followed by lemmatization, with the possibility of adding syntactic, semantic and discourse annotation in a later stage. A core of CoRoLa is described in the article. The target users of our corpus will be researchers in linguistics and language processing, teachers of Romanian, students.</abstract>
<identifier type="citekey">mititelu-etal-2014-corola</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/360_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1235</start>
<end>1239</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CoRoLa — The Reference Corpus of Contemporary Romanian Language
%A Mititelu, Verginica Barbu
%A Irimia, Elena
%A Tufi\textcommabelows, Dan
%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 mititelu-etal-2014-corola
%X We present the project of creating CoRoLa, a reference corpus of contemporary Romanian (from 1945 onwards). In the international context, the project finds its place among the initiatives of gathering huge collections of texts, of pre-processing and annotating them at several levels, and also of documenting them with metadata (CMDI). Our project is a joined effort of two institutes of the Romanian Academy. We foresee a corpus of more than 500 million word forms, covering all functional styles of the language. Although the vast majority of texts will be in written form, we target about 300 hours of oral texts, too, obligatorily with associated transcripts. Most of the texts will be from books, while the rest will be harvested from newspapers, booklets, technical reports, etc. The pre-processing includes cleaning the data and harmonising the diacritics, sentence splitting and tokenization. Annotation will be done at a morphological level in a first stage, followed by lemmatization, with the possibility of adding syntactic, semantic and discourse annotation in a later stage. A core of CoRoLa is described in the article. The target users of our corpus will be researchers in linguistics and language processing, teachers of Romanian, students.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/360_Paper.pdf
%P 1235-1239
Markdown (Informal)
[CoRoLa — The Reference Corpus of Contemporary Romanian Language](http://www.lrec-conf.org/proceedings/lrec2014/pdf/360_Paper.pdf) (Mititelu et al., LREC 2014)
ACL