@inproceedings{cui-etal-2008-corpus,
title = "Corpus Exploitation from {W}ikipedia for Ontology Construction",
author = "Cui, Gaoying and
Lu, Qin and
Li, Wenjie and
Chen, Yirong",
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/541_paper.pdf",
abstract = "Ontology construction usually requires a domain-specific corpus for building corresponding concept hierarchy. The domain corpus must have a good coverage of domain knowledge. Wikipedia(Wiki), the worlds largest online encyclopaedic knowledge source, is open-content, collaboratively edited, and free of charge. It covers millions of articles and still keeps on expanding continuously. These characteristics make Wiki a good candidate as domain corpus resource in ontology construction. However, the selected article collection must have considerable quality and quantity. In this paper, a novel approach is proposed to identify articles in Wiki as domain-specific corpus by using available classification information in Wiki pages. The main idea is to generate a domain hierarchy from the hyperlinked pages of Wiki. Only articles strongly linked to this hierarchy are selected as the domain corpus. The proposed approach makes use of linked category information in Wiki pages to produce the hierarchy as a directed graph for obtaining a set of pages in the same connected branch. Ranking and filtering are then done on these pages based on the classification tree generated by the traversal algorithm. The experiment and evaluation results show that Wiki is a good resource for acquiring a relative high quality domain-specific corpus for ontology construction.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cui-etal-2008-corpus">
<titleInfo>
<title>Corpus Exploitation from Wikipedia for Ontology Construction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gaoying</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qin</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yirong</namePart>
<namePart type="family">Chen</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>Ontology construction usually requires a domain-specific corpus for building corresponding concept hierarchy. The domain corpus must have a good coverage of domain knowledge. Wikipedia(Wiki), the worlds largest online encyclopaedic knowledge source, is open-content, collaboratively edited, and free of charge. It covers millions of articles and still keeps on expanding continuously. These characteristics make Wiki a good candidate as domain corpus resource in ontology construction. However, the selected article collection must have considerable quality and quantity. In this paper, a novel approach is proposed to identify articles in Wiki as domain-specific corpus by using available classification information in Wiki pages. The main idea is to generate a domain hierarchy from the hyperlinked pages of Wiki. Only articles strongly linked to this hierarchy are selected as the domain corpus. The proposed approach makes use of linked category information in Wiki pages to produce the hierarchy as a directed graph for obtaining a set of pages in the same connected branch. Ranking and filtering are then done on these pages based on the classification tree generated by the traversal algorithm. The experiment and evaluation results show that Wiki is a good resource for acquiring a relative high quality domain-specific corpus for ontology construction.</abstract>
<identifier type="citekey">cui-etal-2008-corpus</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/541_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Corpus Exploitation from Wikipedia for Ontology Construction
%A Cui, Gaoying
%A Lu, Qin
%A Li, Wenjie
%A Chen, Yirong
%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 cui-etal-2008-corpus
%X Ontology construction usually requires a domain-specific corpus for building corresponding concept hierarchy. The domain corpus must have a good coverage of domain knowledge. Wikipedia(Wiki), the worlds largest online encyclopaedic knowledge source, is open-content, collaboratively edited, and free of charge. It covers millions of articles and still keeps on expanding continuously. These characteristics make Wiki a good candidate as domain corpus resource in ontology construction. However, the selected article collection must have considerable quality and quantity. In this paper, a novel approach is proposed to identify articles in Wiki as domain-specific corpus by using available classification information in Wiki pages. The main idea is to generate a domain hierarchy from the hyperlinked pages of Wiki. Only articles strongly linked to this hierarchy are selected as the domain corpus. The proposed approach makes use of linked category information in Wiki pages to produce the hierarchy as a directed graph for obtaining a set of pages in the same connected branch. Ranking and filtering are then done on these pages based on the classification tree generated by the traversal algorithm. The experiment and evaluation results show that Wiki is a good resource for acquiring a relative high quality domain-specific corpus for ontology construction.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/541_paper.pdf
Markdown (Informal)
[Corpus Exploitation from Wikipedia for Ontology Construction](http://www.lrec-conf.org/proceedings/lrec2008/pdf/541_paper.pdf) (Cui et al., LREC 2008)
ACL