@inproceedings{de-oliveira-etal-2008-evaluating,
title = "Evaluating Summaries Automatically - A system Proposal",
author = "de Oliveira, Paulo C F and
Torrens, Edson Wilson and
Cidral, Alexandre and
Schossland, Sidney and
Bittencourt, Evandro",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/123_paper.pdf",
abstract = "We propose in this paper an automatic evaluation procedure based on a metric which could provide summary evaluation without human assistance. Our system includes two metrics, which are presented and discussed. The first metric is based on a known and powerful statistical test, the X2 goodness-of-fit test, and has been used in several applications. The second metric is derived from three common metrics used to evaluate Natural Language Processing (NLP) systems, namely precision, recall and f-measure. The combination of these two metrics is intended to allow one to assess the quality of summaries quickly, cheaply and without the need of human intervention, minimizing though, the role of subjective judgment and bias.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-oliveira-etal-2008-evaluating">
<titleInfo>
<title>Evaluating Summaries Automatically - A system Proposal</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paulo</namePart>
<namePart type="given">C</namePart>
<namePart type="given">F</namePart>
<namePart type="family">de Oliveira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edson</namePart>
<namePart type="given">Wilson</namePart>
<namePart type="family">Torrens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandre</namePart>
<namePart type="family">Cidral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sidney</namePart>
<namePart type="family">Schossland</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evandro</namePart>
<namePart type="family">Bittencourt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">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>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose in this paper an automatic evaluation procedure based on a metric which could provide summary evaluation without human assistance. Our system includes two metrics, which are presented and discussed. The first metric is based on a known and powerful statistical test, the X2 goodness-of-fit test, and has been used in several applications. The second metric is derived from three common metrics used to evaluate Natural Language Processing (NLP) systems, namely precision, recall and f-measure. The combination of these two metrics is intended to allow one to assess the quality of summaries quickly, cheaply and without the need of human intervention, minimizing though, the role of subjective judgment and bias.</abstract>
<identifier type="citekey">de-oliveira-etal-2008-evaluating</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/123_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Summaries Automatically - A system Proposal
%A de Oliveira, Paulo C. F.
%A Torrens, Edson Wilson
%A Cidral, Alexandre
%A Schossland, Sidney
%A Bittencourt, Evandro
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F de-oliveira-etal-2008-evaluating
%X We propose in this paper an automatic evaluation procedure based on a metric which could provide summary evaluation without human assistance. Our system includes two metrics, which are presented and discussed. The first metric is based on a known and powerful statistical test, the X2 goodness-of-fit test, and has been used in several applications. The second metric is derived from three common metrics used to evaluate Natural Language Processing (NLP) systems, namely precision, recall and f-measure. The combination of these two metrics is intended to allow one to assess the quality of summaries quickly, cheaply and without the need of human intervention, minimizing though, the role of subjective judgment and bias.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/123_paper.pdf
Markdown (Informal)
[Evaluating Summaries Automatically - A system Proposal](http://www.lrec-conf.org/proceedings/lrec2008/pdf/123_paper.pdf) (de Oliveira et al., LREC 2008)
ACL
- Paulo C F de Oliveira, Edson Wilson Torrens, Alexandre Cidral, Sidney Schossland, and Evandro Bittencourt. 2008. Evaluating Summaries Automatically - A system Proposal. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).