@inproceedings{glaser-kuhn-2014-exploring,
title = "Exploring the utility of coreference chains for improved identification of personal names",
author = "Glaser, Andrea and
Kuhn, Jonas",
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/865_Paper.pdf",
pages = "2570--2577",
abstract = "Identifying the real world entity that a proper name refers to is an important task in many NLP applications. Context plays an important role in disambiguating entities with the same names. In this paper, we discuss a dataset and experimental set-up that allows us to systematically explore the effects of different sizes and types of context in this disambiguation task. We create context by first identifying coreferent expressions in the document and then combining sentences these expressions occur in to one informative context. We apply different filters to obtain different levels of coreference-based context. Since hand-labeling a dataset of a decent size is expensive, we investigate the usefulness of an automatically created pseudo-ambiguity dataset. The results on this pseudo-ambiguity dataset show that using coreference-based context performs better than using a fixed window of context around the entity. The insights taken from the pseudo data experiments can be used to predict how the method works with real data. In our experiments on real data we obtain comparable results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="glaser-kuhn-2014-exploring">
<titleInfo>
<title>Exploring the utility of coreference chains for improved identification of personal names</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Glaser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonas</namePart>
<namePart type="family">Kuhn</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>Identifying the real world entity that a proper name refers to is an important task in many NLP applications. Context plays an important role in disambiguating entities with the same names. In this paper, we discuss a dataset and experimental set-up that allows us to systematically explore the effects of different sizes and types of context in this disambiguation task. We create context by first identifying coreferent expressions in the document and then combining sentences these expressions occur in to one informative context. We apply different filters to obtain different levels of coreference-based context. Since hand-labeling a dataset of a decent size is expensive, we investigate the usefulness of an automatically created pseudo-ambiguity dataset. The results on this pseudo-ambiguity dataset show that using coreference-based context performs better than using a fixed window of context around the entity. The insights taken from the pseudo data experiments can be used to predict how the method works with real data. In our experiments on real data we obtain comparable results.</abstract>
<identifier type="citekey">glaser-kuhn-2014-exploring</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/865_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2570</start>
<end>2577</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring the utility of coreference chains for improved identification of personal names
%A Glaser, Andrea
%A Kuhn, Jonas
%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 glaser-kuhn-2014-exploring
%X Identifying the real world entity that a proper name refers to is an important task in many NLP applications. Context plays an important role in disambiguating entities with the same names. In this paper, we discuss a dataset and experimental set-up that allows us to systematically explore the effects of different sizes and types of context in this disambiguation task. We create context by first identifying coreferent expressions in the document and then combining sentences these expressions occur in to one informative context. We apply different filters to obtain different levels of coreference-based context. Since hand-labeling a dataset of a decent size is expensive, we investigate the usefulness of an automatically created pseudo-ambiguity dataset. The results on this pseudo-ambiguity dataset show that using coreference-based context performs better than using a fixed window of context around the entity. The insights taken from the pseudo data experiments can be used to predict how the method works with real data. In our experiments on real data we obtain comparable results.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/865_Paper.pdf
%P 2570-2577
Markdown (Informal)
[Exploring the utility of coreference chains for improved identification of personal names](http://www.lrec-conf.org/proceedings/lrec2014/pdf/865_Paper.pdf) (Glaser & Kuhn, LREC 2014)
ACL