@inproceedings{lawrie-etal-2012-creating,
title = "Creating and Curating a Cross-Language Person-Entity Linking Collection",
author = "Lawrie, Dawn and
Mayfield, James and
McNamee, Paul and
Oard, Douglas",
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/655_Paper.pdf",
pages = "3106--3110",
abstract = "To stimulate research in cross-language entity linking, we present a new test collection for evaluating the accuracy of cross-language entity linking in twenty-one languages. This paper describes an efficient way to create and curate such a collection, judiciously exploiting existing language resources. Queries are created by semi-automatically identifying person names on the English side of a parallel corpus, using judgments obtained through crowdsourcing to identify the entity corresponding to the name, and projecting the English name onto the non-English document using word alignments. Name projections are then curated, again through crowdsourcing. This technique resulted in the first publicly available multilingual cross-language entity linking collection. The collection includes approximately 55,000 queries, comprising between 875 and 4,329 queries for each of twenty-one non-English languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lawrie-etal-2012-creating">
<titleInfo>
<title>Creating and Curating a Cross-Language Person-Entity Linking Collection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dawn</namePart>
<namePart type="family">Lawrie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Mayfield</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">McNamee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Douglas</namePart>
<namePart type="family">Oard</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>To stimulate research in cross-language entity linking, we present a new test collection for evaluating the accuracy of cross-language entity linking in twenty-one languages. This paper describes an efficient way to create and curate such a collection, judiciously exploiting existing language resources. Queries are created by semi-automatically identifying person names on the English side of a parallel corpus, using judgments obtained through crowdsourcing to identify the entity corresponding to the name, and projecting the English name onto the non-English document using word alignments. Name projections are then curated, again through crowdsourcing. This technique resulted in the first publicly available multilingual cross-language entity linking collection. The collection includes approximately 55,000 queries, comprising between 875 and 4,329 queries for each of twenty-one non-English languages.</abstract>
<identifier type="citekey">lawrie-etal-2012-creating</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/655_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3106</start>
<end>3110</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Creating and Curating a Cross-Language Person-Entity Linking Collection
%A Lawrie, Dawn
%A Mayfield, James
%A McNamee, Paul
%A Oard, Douglas
%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 lawrie-etal-2012-creating
%X To stimulate research in cross-language entity linking, we present a new test collection for evaluating the accuracy of cross-language entity linking in twenty-one languages. This paper describes an efficient way to create and curate such a collection, judiciously exploiting existing language resources. Queries are created by semi-automatically identifying person names on the English side of a parallel corpus, using judgments obtained through crowdsourcing to identify the entity corresponding to the name, and projecting the English name onto the non-English document using word alignments. Name projections are then curated, again through crowdsourcing. This technique resulted in the first publicly available multilingual cross-language entity linking collection. The collection includes approximately 55,000 queries, comprising between 875 and 4,329 queries for each of twenty-one non-English languages.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/655_Paper.pdf
%P 3106-3110
Markdown (Informal)
[Creating and Curating a Cross-Language Person-Entity Linking Collection](http://www.lrec-conf.org/proceedings/lrec2012/pdf/655_Paper.pdf) (Lawrie et al., LREC 2012)
ACL