@inproceedings{vincze-etal-2008-hungarian,
title = "{H}ungarian Word-Sense Disambiguated Corpus",
author = {Vincze, Veronika and
Szarvas, Gy{\"o}rgy and
Alm{\'a}si, Attila and
Szauter, D{\'o}ra and
Orm{\'a}ndi, R{\'o}bert and
Farkas, Rich{\'a}rd and
Hatvani, Csaba and
Csirik, J{\'a}nos},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/847_paper.pdf",
abstract = "To create the first Hungarian WSD corpus, 39 suitable word form samples were selected for the purpose of word sense disambiguation. Among others, selection criteria required the given word form to be frequent in Hungarian language usage, and to have more than one sense considered frequent in usage. HNC and its Heti Vil{\'a}ggazdas{\'a}g subcorpus provided the basis for corpus text selection. This way, each sample has a relevant context (whole article), and information on the lemma, POS-tagging and automatic tokenization is also available. When planning the corpus, 300-500 samples of each word form were to be annotated. This size makes it possible that the subcorpora prepared for the individual word forms can be compared to data available for other languages. However, the finalized database also contains unannotated samples and samples with single annotation, which were annotated only by one of the linguists. The corpus follows the ACLs SensEval/SemEval WSD tasks format. The first version of the corpus was developed within the scope of the project titled The construction Hungarian WordNet Ontology and its application in Information Extraction Systems (Hatvani et al., 2007). The corpus for research and educational purposes is available and can be downloaded free of charge.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vincze-etal-2008-hungarian">
<titleInfo>
<title>Hungarian Word-Sense Disambiguated Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Veronika</namePart>
<namePart type="family">Vincze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">György</namePart>
<namePart type="family">Szarvas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Attila</namePart>
<namePart type="family">Almási</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dóra</namePart>
<namePart type="family">Szauter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Róbert</namePart>
<namePart type="family">Ormándi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richárd</namePart>
<namePart type="family">Farkas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Csaba</namePart>
<namePart type="family">Hatvani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">János</namePart>
<namePart type="family">Csirik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To create the first Hungarian WSD corpus, 39 suitable word form samples were selected for the purpose of word sense disambiguation. Among others, selection criteria required the given word form to be frequent in Hungarian language usage, and to have more than one sense considered frequent in usage. HNC and its Heti Világgazdaság subcorpus provided the basis for corpus text selection. This way, each sample has a relevant context (whole article), and information on the lemma, POS-tagging and automatic tokenization is also available. When planning the corpus, 300-500 samples of each word form were to be annotated. This size makes it possible that the subcorpora prepared for the individual word forms can be compared to data available for other languages. However, the finalized database also contains unannotated samples and samples with single annotation, which were annotated only by one of the linguists. The corpus follows the ACLs SensEval/SemEval WSD tasks format. The first version of the corpus was developed within the scope of the project titled The construction Hungarian WordNet Ontology and its application in Information Extraction Systems (Hatvani et al., 2007). The corpus for research and educational purposes is available and can be downloaded free of charge.</abstract>
<identifier type="citekey">vincze-etal-2008-hungarian</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/847_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hungarian Word-Sense Disambiguated Corpus
%A Vincze, Veronika
%A Szarvas, György
%A Almási, Attila
%A Szauter, Dóra
%A Ormándi, Róbert
%A Farkas, Richárd
%A Hatvani, Csaba
%A Csirik, János
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F vincze-etal-2008-hungarian
%X To create the first Hungarian WSD corpus, 39 suitable word form samples were selected for the purpose of word sense disambiguation. Among others, selection criteria required the given word form to be frequent in Hungarian language usage, and to have more than one sense considered frequent in usage. HNC and its Heti Világgazdaság subcorpus provided the basis for corpus text selection. This way, each sample has a relevant context (whole article), and information on the lemma, POS-tagging and automatic tokenization is also available. When planning the corpus, 300-500 samples of each word form were to be annotated. This size makes it possible that the subcorpora prepared for the individual word forms can be compared to data available for other languages. However, the finalized database also contains unannotated samples and samples with single annotation, which were annotated only by one of the linguists. The corpus follows the ACLs SensEval/SemEval WSD tasks format. The first version of the corpus was developed within the scope of the project titled The construction Hungarian WordNet Ontology and its application in Information Extraction Systems (Hatvani et al., 2007). The corpus for research and educational purposes is available and can be downloaded free of charge.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/847_paper.pdf
Markdown (Informal)
[Hungarian Word-Sense Disambiguated Corpus](http://www.lrec-conf.org/proceedings/lrec2008/pdf/847_paper.pdf) (Vincze et al., LREC 2008)
ACL
- Veronika Vincze, György Szarvas, Attila Almási, Dóra Szauter, Róbert Ormándi, Richárd Farkas, Csaba Hatvani, and János Csirik. 2008. Hungarian Word-Sense Disambiguated Corpus. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).