@inproceedings{ion-etal-2012-rombac,
title = "{ROMBAC}: The {R}omanian Balanced Annotated Corpus",
author = "Ion, Radu and
Irimia, Elena and
{\c{S}}tef{\u{a}}nescu, Dan and
Tufi{\textcommabelow{s}}, Dan",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/218_Paper.pdf",
pages = "339--344",
abstract = "This article describes the collecting, processing and validation of a large balanced corpus for Romanian. The annotation types and structure of the corpus are briefly reviewed. It was constructed at the Research Institute for Artificial Intelligence of the Romanian Academy in the context of an international project (METANET4U). The processing covers tokenization, POS-tagging, lemmatization and chunking. The corpus is in XML format generated by our in-house annotation tools; the corpus encoding schema is XCES compliant and the metadata specification is conformant to the METANET recommendations. To the best of our knowledge, this is the first large and richly annotated corpus for Romanian. ROMBAC is intended to be the foundation of a linguistic environment containing a reference corpus for contemporary Romanian and a comprehensive collection of interoperable processing tools.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ion-etal-2012-rombac">
<titleInfo>
<title>ROMBAC: The Romanian Balanced Annotated Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Radu</namePart>
<namePart type="family">Ion</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">Ştefănescu</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>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This article describes the collecting, processing and validation of a large balanced corpus for Romanian. The annotation types and structure of the corpus are briefly reviewed. It was constructed at the Research Institute for Artificial Intelligence of the Romanian Academy in the context of an international project (METANET4U). The processing covers tokenization, POS-tagging, lemmatization and chunking. The corpus is in XML format generated by our in-house annotation tools; the corpus encoding schema is XCES compliant and the metadata specification is conformant to the METANET recommendations. To the best of our knowledge, this is the first large and richly annotated corpus for Romanian. ROMBAC is intended to be the foundation of a linguistic environment containing a reference corpus for contemporary Romanian and a comprehensive collection of interoperable processing tools.</abstract>
<identifier type="citekey">ion-etal-2012-rombac</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/218_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>339</start>
<end>344</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ROMBAC: The Romanian Balanced Annotated Corpus
%A Ion, Radu
%A Irimia, Elena
%A Ştefănescu, Dan
%A Tufi\textcommabelows, Dan
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F ion-etal-2012-rombac
%X This article describes the collecting, processing and validation of a large balanced corpus for Romanian. The annotation types and structure of the corpus are briefly reviewed. It was constructed at the Research Institute for Artificial Intelligence of the Romanian Academy in the context of an international project (METANET4U). The processing covers tokenization, POS-tagging, lemmatization and chunking. The corpus is in XML format generated by our in-house annotation tools; the corpus encoding schema is XCES compliant and the metadata specification is conformant to the METANET recommendations. To the best of our knowledge, this is the first large and richly annotated corpus for Romanian. ROMBAC is intended to be the foundation of a linguistic environment containing a reference corpus for contemporary Romanian and a comprehensive collection of interoperable processing tools.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/218_Paper.pdf
%P 339-344
Markdown (Informal)
[ROMBAC: The Romanian Balanced Annotated Corpus](http://www.lrec-conf.org/proceedings/lrec2012/pdf/218_Paper.pdf) (Ion et al., LREC 2012)
ACL
- Radu Ion, Elena Irimia, Dan Ştefănescu, and Dan Tufiș. 2012. ROMBAC: The Romanian Balanced Annotated Corpus. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 339–344, Istanbul, Turkey. European Language Resources Association (ELRA).