@inproceedings{simov-etal-2004-language,
title = "A Language Resources Infrastructure for {B}ulgarian",
author = "Simov, Kiril and
Osenova, Petya and
Kolkovska, Sia and
Balabanova, Elisaveta and
Doikoff, Dimitar",
editor = "Lino, Maria Teresa and
Xavier, Maria Francisca and
Ferreira, F{\'a}tima and
Costa, Rute and
Silva, Raquel",
booktitle = "Proceedings of the Fourth International Conference on Language Resources and Evaluation ({LREC}{'}04)",
month = may,
year = "2004",
address = "Lisbon, Portugal",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2004/pdf/316.pdf",
abstract = "This paper describes the infrastructure of a basic language resources set for Bulgarian in the context of BLARK initiative requirements. We focus on the treebanking task as a trigger for basic language resources compilation. Two strategies have been applied in this respect: (1) implementing the main pre-processing modules before the treebank compilation and (2) creating more elaborate types of resources in parallel to the treebank compilation. The description of language resources within BulTreeBank project is divided into two parts: language technology, which includes tokenization, morphosyntactic analyzer, morphosyntactic disambiguation, partial grammars, and language data, which includes the layers of the BulTreeBank corpus and the variety of lexicons. The advantages of our approach to a less-spoken language (like Bulgarian) are as follows: it triggers the creation of the basic set of language resources which lack for certain languages and it rises the question about the ways of language resources creation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="simov-etal-2004-language">
<titleInfo>
<title>A Language Resources Infrastructure for Bulgarian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kiril</namePart>
<namePart type="family">Simov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petya</namePart>
<namePart type="family">Osenova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sia</namePart>
<namePart type="family">Kolkovska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisaveta</namePart>
<namePart type="family">Balabanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dimitar</namePart>
<namePart type="family">Doikoff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2004-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Teresa</namePart>
<namePart type="family">Lino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Francisca</namePart>
<namePart type="family">Xavier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fátima</namePart>
<namePart type="family">Ferreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rute</namePart>
<namePart type="family">Costa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="family">Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Lisbon, Portugal</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the infrastructure of a basic language resources set for Bulgarian in the context of BLARK initiative requirements. We focus on the treebanking task as a trigger for basic language resources compilation. Two strategies have been applied in this respect: (1) implementing the main pre-processing modules before the treebank compilation and (2) creating more elaborate types of resources in parallel to the treebank compilation. The description of language resources within BulTreeBank project is divided into two parts: language technology, which includes tokenization, morphosyntactic analyzer, morphosyntactic disambiguation, partial grammars, and language data, which includes the layers of the BulTreeBank corpus and the variety of lexicons. The advantages of our approach to a less-spoken language (like Bulgarian) are as follows: it triggers the creation of the basic set of language resources which lack for certain languages and it rises the question about the ways of language resources creation.</abstract>
<identifier type="citekey">simov-etal-2004-language</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2004/pdf/316.pdf</url>
</location>
<part>
<date>2004-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Language Resources Infrastructure for Bulgarian
%A Simov, Kiril
%A Osenova, Petya
%A Kolkovska, Sia
%A Balabanova, Elisaveta
%A Doikoff, Dimitar
%Y Lino, Maria Teresa
%Y Xavier, Maria Francisca
%Y Ferreira, Fátima
%Y Costa, Rute
%Y Silva, Raquel
%S Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04)
%D 2004
%8 May
%I European Language Resources Association (ELRA)
%C Lisbon, Portugal
%F simov-etal-2004-language
%X This paper describes the infrastructure of a basic language resources set for Bulgarian in the context of BLARK initiative requirements. We focus on the treebanking task as a trigger for basic language resources compilation. Two strategies have been applied in this respect: (1) implementing the main pre-processing modules before the treebank compilation and (2) creating more elaborate types of resources in parallel to the treebank compilation. The description of language resources within BulTreeBank project is divided into two parts: language technology, which includes tokenization, morphosyntactic analyzer, morphosyntactic disambiguation, partial grammars, and language data, which includes the layers of the BulTreeBank corpus and the variety of lexicons. The advantages of our approach to a less-spoken language (like Bulgarian) are as follows: it triggers the creation of the basic set of language resources which lack for certain languages and it rises the question about the ways of language resources creation.
%U http://www.lrec-conf.org/proceedings/lrec2004/pdf/316.pdf
Markdown (Informal)
[A Language Resources Infrastructure for Bulgarian](http://www.lrec-conf.org/proceedings/lrec2004/pdf/316.pdf) (Simov et al., LREC 2004)
ACL
- Kiril Simov, Petya Osenova, Sia Kolkovska, Elisaveta Balabanova, and Dimitar Doikoff. 2004. A Language Resources Infrastructure for Bulgarian. In Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04), Lisbon, Portugal. European Language Resources Association (ELRA).