@inproceedings{koeva-etal-2010-bulgarian,
title = "{B}ulgarian National Corpus Project",
author = "Koeva, Svetla and
Blagoeva, Diana and
Kolkovska, Siya",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/316_Paper.pdf",
abstract = "The paper presents Bulgarian National Corpus project (BulNC) - a large-scale, representative, online available corpus of Bulgarian. The BulNC is also a monolingual general corpus, fully morpho-syntactically (and partially semantically) annotated, and manually provided with detailed meta-data descriptions. Presently the Bulgarian National corpus consists of about 320 000 000 graphical words and includes more than 10 000 samples. Briefly the corpus structure and the accepted criteria for representativeness and well-balancing are presented. The query language for advance search of collocations and concordances is demonstrated with some examples - it allows to retrieve word combinations, ordered queries, inflexionally and semantically related words, part-of-speech tags, utilising Boolean operations and grouping as well. The BulNC already plays a significant role in natural language processing of Bulgarian contributing to scientific advances in spelling and grammar checking, word sense disambiguation, speech recognition, text categorisation, topic extraction and machine translation. The BulNC can also be used in different investigations going beyond the linguistics: library studies, social sciences research, teaching methods studies, etc.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="koeva-etal-2010-bulgarian">
<titleInfo>
<title>Bulgarian National Corpus Project</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">Diana</namePart>
<namePart type="family">Blagoeva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siya</namePart>
<namePart type="family">Kolkovska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">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>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The paper presents Bulgarian National Corpus project (BulNC) - a large-scale, representative, online available corpus of Bulgarian. The BulNC is also a monolingual general corpus, fully morpho-syntactically (and partially semantically) annotated, and manually provided with detailed meta-data descriptions. Presently the Bulgarian National corpus consists of about 320 000 000 graphical words and includes more than 10 000 samples. Briefly the corpus structure and the accepted criteria for representativeness and well-balancing are presented. The query language for advance search of collocations and concordances is demonstrated with some examples - it allows to retrieve word combinations, ordered queries, inflexionally and semantically related words, part-of-speech tags, utilising Boolean operations and grouping as well. The BulNC already plays a significant role in natural language processing of Bulgarian contributing to scientific advances in spelling and grammar checking, word sense disambiguation, speech recognition, text categorisation, topic extraction and machine translation. The BulNC can also be used in different investigations going beyond the linguistics: library studies, social sciences research, teaching methods studies, etc.</abstract>
<identifier type="citekey">koeva-etal-2010-bulgarian</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/316_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bulgarian National Corpus Project
%A Koeva, Svetla
%A Blagoeva, Diana
%A Kolkovska, Siya
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F koeva-etal-2010-bulgarian
%X The paper presents Bulgarian National Corpus project (BulNC) - a large-scale, representative, online available corpus of Bulgarian. The BulNC is also a monolingual general corpus, fully morpho-syntactically (and partially semantically) annotated, and manually provided with detailed meta-data descriptions. Presently the Bulgarian National corpus consists of about 320 000 000 graphical words and includes more than 10 000 samples. Briefly the corpus structure and the accepted criteria for representativeness and well-balancing are presented. The query language for advance search of collocations and concordances is demonstrated with some examples - it allows to retrieve word combinations, ordered queries, inflexionally and semantically related words, part-of-speech tags, utilising Boolean operations and grouping as well. The BulNC already plays a significant role in natural language processing of Bulgarian contributing to scientific advances in spelling and grammar checking, word sense disambiguation, speech recognition, text categorisation, topic extraction and machine translation. The BulNC can also be used in different investigations going beyond the linguistics: library studies, social sciences research, teaching methods studies, etc.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/316_Paper.pdf
Markdown (Informal)
[Bulgarian National Corpus Project](http://www.lrec-conf.org/proceedings/lrec2010/pdf/316_Paper.pdf) (Koeva et al., LREC 2010)
ACL
- Svetla Koeva, Diana Blagoeva, and Siya Kolkovska. 2010. Bulgarian National Corpus Project. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).