@inproceedings{hong-etal-2014-repository,
title = "A Repository of State of the Art and Competitive Baseline Summaries for Generic News Summarization",
author = "Hong, Kai and
Conroy, John and
Favre, Benoit and
Kulesza, Alex and
Lin, Hui and
Nenkova, Ani",
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/1093_Paper.pdf",
pages = "1608--1616",
abstract = "In the period since 2004, many novel sophisticated approaches for generic multi-document summarization have been developed. Intuitive simple approaches have also been shown to perform unexpectedly well for the task. Yet it is practically impossible to compare the existing approaches directly, because systems have been evaluated on different datasets, with different evaluation measures, against different sets of comparison systems. Here we present a corpus of summaries produced by several state-of-the-art extractive summarization systems or by popular baseline systems. The inputs come from the 2004 DUC evaluation, the latest year in which generic summarization was addressed in a shared task. We use the same settings for ROUGE automatic evaluation to compare the systems directly and analyze the statistical significance of the differences in performance. We show that in terms of average scores the state-of-the-art systems appear similar but that in fact they produce very different summaries. Our corpus will facilitate future research on generic summarization and motivates the need for development of more sensitive evaluation measures and for approaches to system combination in summarization.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hong-etal-2014-repository">
<titleInfo>
<title>A Repository of State of the Art and Competitive Baseline Summaries for Generic News Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Conroy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benoit</namePart>
<namePart type="family">Favre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Kulesza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ani</namePart>
<namePart type="family">Nenkova</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 the period since 2004, many novel sophisticated approaches for generic multi-document summarization have been developed. Intuitive simple approaches have also been shown to perform unexpectedly well for the task. Yet it is practically impossible to compare the existing approaches directly, because systems have been evaluated on different datasets, with different evaluation measures, against different sets of comparison systems. Here we present a corpus of summaries produced by several state-of-the-art extractive summarization systems or by popular baseline systems. The inputs come from the 2004 DUC evaluation, the latest year in which generic summarization was addressed in a shared task. We use the same settings for ROUGE automatic evaluation to compare the systems directly and analyze the statistical significance of the differences in performance. We show that in terms of average scores the state-of-the-art systems appear similar but that in fact they produce very different summaries. Our corpus will facilitate future research on generic summarization and motivates the need for development of more sensitive evaluation measures and for approaches to system combination in summarization.</abstract>
<identifier type="citekey">hong-etal-2014-repository</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/1093_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1608</start>
<end>1616</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Repository of State of the Art and Competitive Baseline Summaries for Generic News Summarization
%A Hong, Kai
%A Conroy, John
%A Favre, Benoit
%A Kulesza, Alex
%A Lin, Hui
%A Nenkova, Ani
%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 hong-etal-2014-repository
%X In the period since 2004, many novel sophisticated approaches for generic multi-document summarization have been developed. Intuitive simple approaches have also been shown to perform unexpectedly well for the task. Yet it is practically impossible to compare the existing approaches directly, because systems have been evaluated on different datasets, with different evaluation measures, against different sets of comparison systems. Here we present a corpus of summaries produced by several state-of-the-art extractive summarization systems or by popular baseline systems. The inputs come from the 2004 DUC evaluation, the latest year in which generic summarization was addressed in a shared task. We use the same settings for ROUGE automatic evaluation to compare the systems directly and analyze the statistical significance of the differences in performance. We show that in terms of average scores the state-of-the-art systems appear similar but that in fact they produce very different summaries. Our corpus will facilitate future research on generic summarization and motivates the need for development of more sensitive evaluation measures and for approaches to system combination in summarization.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/1093_Paper.pdf
%P 1608-1616
Markdown (Informal)
[A Repository of State of the Art and Competitive Baseline Summaries for Generic News Summarization](http://www.lrec-conf.org/proceedings/lrec2014/pdf/1093_Paper.pdf) (Hong et al., LREC 2014)
ACL