@inproceedings{agirre-etal-2012-matching,
title = "Matching Cultural Heritage items to {W}ikipedia",
author = "Agirre, Eneko and
Barrena, Ander and
de Lacalle, Oier Lopez and
Soroa, Aitor and
Fernando, Samuel and
Stevenson, Mark",
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/1021_Paper.pdf",
pages = "1729--1735",
abstract = "Digitised Cultural Heritage (CH) items usually have short descriptions and lack rich contextual information. Wikipedia articles, on the contrary, include in-depth descriptions and links to related articles, which motivate the enrichment of CH items with information from Wikipedia. In this paper we explore the feasibility of finding matching articles in Wikipedia for a given Cultural Heritage item. We manually annotated a random sample of items from Europeana, and performed a qualitative and quantitative study of the issues and problems that arise, showing that each kind of CH item is different and needs a nuanced definition of what ``matching article'' means. In addition, we test a well-known wikification (aka entity linking) algorithm on the task. Our results indicate that a substantial number of items can be effectively linked to their corresponding Wikipedia article.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="agirre-etal-2012-matching">
<titleInfo>
<title>Matching Cultural Heritage items to Wikipedia</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eneko</namePart>
<namePart type="family">Agirre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ander</namePart>
<namePart type="family">Barrena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oier</namePart>
<namePart type="given">Lopez</namePart>
<namePart type="family">de Lacalle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aitor</namePart>
<namePart type="family">Soroa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Fernando</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Stevenson</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>Digitised Cultural Heritage (CH) items usually have short descriptions and lack rich contextual information. Wikipedia articles, on the contrary, include in-depth descriptions and links to related articles, which motivate the enrichment of CH items with information from Wikipedia. In this paper we explore the feasibility of finding matching articles in Wikipedia for a given Cultural Heritage item. We manually annotated a random sample of items from Europeana, and performed a qualitative and quantitative study of the issues and problems that arise, showing that each kind of CH item is different and needs a nuanced definition of what “matching article” means. In addition, we test a well-known wikification (aka entity linking) algorithm on the task. Our results indicate that a substantial number of items can be effectively linked to their corresponding Wikipedia article.</abstract>
<identifier type="citekey">agirre-etal-2012-matching</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/1021_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>1729</start>
<end>1735</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Matching Cultural Heritage items to Wikipedia
%A Agirre, Eneko
%A Barrena, Ander
%A de Lacalle, Oier Lopez
%A Soroa, Aitor
%A Fernando, Samuel
%A Stevenson, Mark
%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 agirre-etal-2012-matching
%X Digitised Cultural Heritage (CH) items usually have short descriptions and lack rich contextual information. Wikipedia articles, on the contrary, include in-depth descriptions and links to related articles, which motivate the enrichment of CH items with information from Wikipedia. In this paper we explore the feasibility of finding matching articles in Wikipedia for a given Cultural Heritage item. We manually annotated a random sample of items from Europeana, and performed a qualitative and quantitative study of the issues and problems that arise, showing that each kind of CH item is different and needs a nuanced definition of what “matching article” means. In addition, we test a well-known wikification (aka entity linking) algorithm on the task. Our results indicate that a substantial number of items can be effectively linked to their corresponding Wikipedia article.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/1021_Paper.pdf
%P 1729-1735
Markdown (Informal)
[Matching Cultural Heritage items to Wikipedia](http://www.lrec-conf.org/proceedings/lrec2012/pdf/1021_Paper.pdf) (Agirre et al., LREC 2012)
ACL
- Eneko Agirre, Ander Barrena, Oier Lopez de Lacalle, Aitor Soroa, Samuel Fernando, and Mark Stevenson. 2012. Matching Cultural Heritage items to Wikipedia. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 1729–1735, Istanbul, Turkey. European Language Resources Association (ELRA).