@inproceedings{koeva-etal-2012-bulgarian,
title = "{B}ulgarian {X}-language Parallel Corpus",
author = "Koeva, Svetla and
Stoyanova, Ivelina and
Dekova, Rositsa and
Rizov, Borislav and
Genov, Angel",
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/587_Paper.pdf",
pages = "2480--2486",
abstract = "The paper presents the methodology and the outcome of the compilation and the processing of the Bulgarian X-language Parallel Corpus (Bul-X-Cor) which was integrated as part of the Bulgarian National Corpus (BulNC). We focus on building representative parallel corpora which include a diversity of domains and genres, reflect the relations between Bulgarian and other languages and are consistent in terms of compilation methodology, text representation, metadata description and annotation conventions. The approaches implemented in the construction of Bul-X-Cor include using readily available text collections on the web, manual compilation (by means of Internet browsing) and preferably automatic compilation (by means of web crawling ― general and focused). Certain levels of annotation applied to Bul-X-Cor are taken as obligatory (sentence segmentation and sentence alignment), while others depend on the availability of tools for a particular language (morpho-syntactic tagging, lemmatisation, syntactic parsing, named entity recognition, word sense disambiguation, etc.) or for a particular task (word and clause alignment). To achieve uniformity of the annotation we have either annotated raw data from scratch or transformed the already existing annotation to follow the conventions accepted for BulNC. Finally, actual uses of the corpora are presented and conclusions are drawn with respect to future work.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="koeva-etal-2012-bulgarian">
<titleInfo>
<title>Bulgarian X-language Parallel Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Svetla</namePart>
<namePart type="family">Koeva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivelina</namePart>
<namePart type="family">Stoyanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rositsa</namePart>
<namePart type="family">Dekova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Borislav</namePart>
<namePart type="family">Rizov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angel</namePart>
<namePart type="family">Genov</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>The paper presents the methodology and the outcome of the compilation and the processing of the Bulgarian X-language Parallel Corpus (Bul-X-Cor) which was integrated as part of the Bulgarian National Corpus (BulNC). We focus on building representative parallel corpora which include a diversity of domains and genres, reflect the relations between Bulgarian and other languages and are consistent in terms of compilation methodology, text representation, metadata description and annotation conventions. The approaches implemented in the construction of Bul-X-Cor include using readily available text collections on the web, manual compilation (by means of Internet browsing) and preferably automatic compilation (by means of web crawling ― general and focused). Certain levels of annotation applied to Bul-X-Cor are taken as obligatory (sentence segmentation and sentence alignment), while others depend on the availability of tools for a particular language (morpho-syntactic tagging, lemmatisation, syntactic parsing, named entity recognition, word sense disambiguation, etc.) or for a particular task (word and clause alignment). To achieve uniformity of the annotation we have either annotated raw data from scratch or transformed the already existing annotation to follow the conventions accepted for BulNC. Finally, actual uses of the corpora are presented and conclusions are drawn with respect to future work.</abstract>
<identifier type="citekey">koeva-etal-2012-bulgarian</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/587_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2480</start>
<end>2486</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bulgarian X-language Parallel Corpus
%A Koeva, Svetla
%A Stoyanova, Ivelina
%A Dekova, Rositsa
%A Rizov, Borislav
%A Genov, Angel
%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 koeva-etal-2012-bulgarian
%X The paper presents the methodology and the outcome of the compilation and the processing of the Bulgarian X-language Parallel Corpus (Bul-X-Cor) which was integrated as part of the Bulgarian National Corpus (BulNC). We focus on building representative parallel corpora which include a diversity of domains and genres, reflect the relations between Bulgarian and other languages and are consistent in terms of compilation methodology, text representation, metadata description and annotation conventions. The approaches implemented in the construction of Bul-X-Cor include using readily available text collections on the web, manual compilation (by means of Internet browsing) and preferably automatic compilation (by means of web crawling ― general and focused). Certain levels of annotation applied to Bul-X-Cor are taken as obligatory (sentence segmentation and sentence alignment), while others depend on the availability of tools for a particular language (morpho-syntactic tagging, lemmatisation, syntactic parsing, named entity recognition, word sense disambiguation, etc.) or for a particular task (word and clause alignment). To achieve uniformity of the annotation we have either annotated raw data from scratch or transformed the already existing annotation to follow the conventions accepted for BulNC. Finally, actual uses of the corpora are presented and conclusions are drawn with respect to future work.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/587_Paper.pdf
%P 2480-2486
Markdown (Informal)
[Bulgarian X-language Parallel Corpus](http://www.lrec-conf.org/proceedings/lrec2012/pdf/587_Paper.pdf) (Koeva et al., LREC 2012)
ACL
- Svetla Koeva, Ivelina Stoyanova, Rositsa Dekova, Borislav Rizov, and Angel Genov. 2012. Bulgarian X-language Parallel Corpus. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2480–2486, Istanbul, Turkey. European Language Resources Association (ELRA).