@inproceedings{jacquet-etal-2014-clustering,
title = "Clustering of Multi-Word Named Entity variants: Multilingual Evaluation",
author = "Jacquet, Guillaume and
Ehrmann, Maud and
Steinberger, Ralf",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/468_Paper.pdf",
pages = "2548--2553",
abstract = "Multi-word entities, such as organisation names, are frequently written in many different ways. We have previously automatically identified over one million acronym pairs in 22 languages, consisting of their short form (e.g. EC) and their corresponding long forms (e.g. European Commission, European Union Commission). In order to automatically group such long form variants as belonging to the same entity, we cluster them, using bottom-up hierarchical clustering and pair-wise string similarity metrics. In this paper, we address the issue of how to evaluate the named entity variant clusters automatically, with minimal human annotation effort. We present experiments that make use of Wikipedia redirection tables and we show that this method produces good results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jacquet-etal-2014-clustering">
<titleInfo>
<title>Clustering of Multi-Word Named Entity variants: Multilingual Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guillaume</namePart>
<namePart type="family">Jacquet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maud</namePart>
<namePart type="family">Ehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ralf</namePart>
<namePart type="family">Steinberger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multi-word entities, such as organisation names, are frequently written in many different ways. We have previously automatically identified over one million acronym pairs in 22 languages, consisting of their short form (e.g. EC) and their corresponding long forms (e.g. European Commission, European Union Commission). In order to automatically group such long form variants as belonging to the same entity, we cluster them, using bottom-up hierarchical clustering and pair-wise string similarity metrics. In this paper, we address the issue of how to evaluate the named entity variant clusters automatically, with minimal human annotation effort. We present experiments that make use of Wikipedia redirection tables and we show that this method produces good results.</abstract>
<identifier type="citekey">jacquet-etal-2014-clustering</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/468_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2548</start>
<end>2553</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Clustering of Multi-Word Named Entity variants: Multilingual Evaluation
%A Jacquet, Guillaume
%A Ehrmann, Maud
%A Steinberger, Ralf
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F jacquet-etal-2014-clustering
%X Multi-word entities, such as organisation names, are frequently written in many different ways. We have previously automatically identified over one million acronym pairs in 22 languages, consisting of their short form (e.g. EC) and their corresponding long forms (e.g. European Commission, European Union Commission). In order to automatically group such long form variants as belonging to the same entity, we cluster them, using bottom-up hierarchical clustering and pair-wise string similarity metrics. In this paper, we address the issue of how to evaluate the named entity variant clusters automatically, with minimal human annotation effort. We present experiments that make use of Wikipedia redirection tables and we show that this method produces good results.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/468_Paper.pdf
%P 2548-2553
Markdown (Informal)
[Clustering of Multi-Word Named Entity variants: Multilingual Evaluation](http://www.lrec-conf.org/proceedings/lrec2014/pdf/468_Paper.pdf) (Jacquet et al., LREC 2014)
ACL