@inproceedings{cybulska-vossen-2014-using,
title = "Using a sledgehammer to crack a nut? Lexical diversity and event coreference resolution",
author = "Cybulska, Agata and
Vossen, Piek",
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/840_Paper.pdf",
pages = "4545--4552",
abstract = "In this paper we examine the representativeness of the EventCorefBank (ECB, Bejan and Harabagiu, 2010) with regards to the language population of large-volume streams of news. The ECB corpus is one of the data sets used for evaluation of the task of event coreference resolution. Our analysis shows that the ECB in most cases covers one seminal event per domain, what considerably simplifies event and so language diversity that one comes across in the news. We augmented the corpus with a new corpus component, consisting of 502 texts, describing different instances of event types that were already captured by the 43 topics of the ECB, making it more representative of news articles on the web. The new {``}ECB+{''} corpus is available for further research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cybulska-vossen-2014-using">
<titleInfo>
<title>Using a sledgehammer to crack a nut? Lexical diversity and event coreference resolution</title>
</titleInfo>
<name type="personal">
<namePart type="given">Agata</namePart>
<namePart type="family">Cybulska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piek</namePart>
<namePart type="family">Vossen</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>In this paper we examine the representativeness of the EventCorefBank (ECB, Bejan and Harabagiu, 2010) with regards to the language population of large-volume streams of news. The ECB corpus is one of the data sets used for evaluation of the task of event coreference resolution. Our analysis shows that the ECB in most cases covers one seminal event per domain, what considerably simplifies event and so language diversity that one comes across in the news. We augmented the corpus with a new corpus component, consisting of 502 texts, describing different instances of event types that were already captured by the 43 topics of the ECB, making it more representative of news articles on the web. The new “ECB+” corpus is available for further research.</abstract>
<identifier type="citekey">cybulska-vossen-2014-using</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/840_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>4545</start>
<end>4552</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using a sledgehammer to crack a nut? Lexical diversity and event coreference resolution
%A Cybulska, Agata
%A Vossen, Piek
%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 cybulska-vossen-2014-using
%X In this paper we examine the representativeness of the EventCorefBank (ECB, Bejan and Harabagiu, 2010) with regards to the language population of large-volume streams of news. The ECB corpus is one of the data sets used for evaluation of the task of event coreference resolution. Our analysis shows that the ECB in most cases covers one seminal event per domain, what considerably simplifies event and so language diversity that one comes across in the news. We augmented the corpus with a new corpus component, consisting of 502 texts, describing different instances of event types that were already captured by the 43 topics of the ECB, making it more representative of news articles on the web. The new “ECB+” corpus is available for further research.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/840_Paper.pdf
%P 4545-4552
Markdown (Informal)
[Using a sledgehammer to crack a nut? Lexical diversity and event coreference resolution](http://www.lrec-conf.org/proceedings/lrec2014/pdf/840_Paper.pdf) (Cybulska & Vossen, LREC 2014)
ACL