@inproceedings{almeida-etal-2014-priberam,
title = "Priberam Compressive Summarization Corpus: A New Multi-Document Summarization Corpus for {E}uropean {P}ortuguese",
author = "Almeida, Miguel B. and
Almeida, Mariana S. C. and
Martins, Andr{\'e} F. T. and
Figueira, Helena and
Mendes, Pedro and
Pinto, Cl{\'a}udia",
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/187_Paper.pdf",
pages = "146--152",
abstract = "In this paper, we introduce the Priberam Compressive Summarization Corpus, a new multi-document summarization corpus for European Portuguese. The corpus follows the format of the summarization corpora for English in recent DUC and TAC conferences. It contains 80 manually chosen topics referring to events occurred between 2010 and 2013. Each topic contains 10 news stories from major Portuguese newspapers, radio and TV stations, along with two human generated summaries up to 100 words. Apart from the language, one important difference from the DUC/TAC setup is that the human summaries in our corpus are \textit{compressive}: the annotators performed only sentence and word deletion operations, as opposed to generating summaries from scratch. We use this corpus to train and evaluate learning-based extractive and compressive summarization systems, providing an empirical comparison between these two approaches. The corpus is made freely available in order to facilitate research on automatic summarization.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="almeida-etal-2014-priberam">
<titleInfo>
<title>Priberam Compressive Summarization Corpus: A New Multi-Document Summarization Corpus for European Portuguese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Miguel</namePart>
<namePart type="given">B</namePart>
<namePart type="family">Almeida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariana</namePart>
<namePart type="given">S</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Almeida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="given">F</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Figueira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="family">Mendes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cláudia</namePart>
<namePart type="family">Pinto</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 introduce the Priberam Compressive Summarization Corpus, a new multi-document summarization corpus for European Portuguese. The corpus follows the format of the summarization corpora for English in recent DUC and TAC conferences. It contains 80 manually chosen topics referring to events occurred between 2010 and 2013. Each topic contains 10 news stories from major Portuguese newspapers, radio and TV stations, along with two human generated summaries up to 100 words. Apart from the language, one important difference from the DUC/TAC setup is that the human summaries in our corpus are compressive: the annotators performed only sentence and word deletion operations, as opposed to generating summaries from scratch. We use this corpus to train and evaluate learning-based extractive and compressive summarization systems, providing an empirical comparison between these two approaches. The corpus is made freely available in order to facilitate research on automatic summarization.</abstract>
<identifier type="citekey">almeida-etal-2014-priberam</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/187_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>146</start>
<end>152</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Priberam Compressive Summarization Corpus: A New Multi-Document Summarization Corpus for European Portuguese
%A Almeida, Miguel B.
%A Almeida, Mariana S. C.
%A Martins, André F. T.
%A Figueira, Helena
%A Mendes, Pedro
%A Pinto, Cláudia
%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 almeida-etal-2014-priberam
%X In this paper, we introduce the Priberam Compressive Summarization Corpus, a new multi-document summarization corpus for European Portuguese. The corpus follows the format of the summarization corpora for English in recent DUC and TAC conferences. It contains 80 manually chosen topics referring to events occurred between 2010 and 2013. Each topic contains 10 news stories from major Portuguese newspapers, radio and TV stations, along with two human generated summaries up to 100 words. Apart from the language, one important difference from the DUC/TAC setup is that the human summaries in our corpus are compressive: the annotators performed only sentence and word deletion operations, as opposed to generating summaries from scratch. We use this corpus to train and evaluate learning-based extractive and compressive summarization systems, providing an empirical comparison between these two approaches. The corpus is made freely available in order to facilitate research on automatic summarization.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/187_Paper.pdf
%P 146-152
Markdown (Informal)
[Priberam Compressive Summarization Corpus: A New Multi-Document Summarization Corpus for European Portuguese](http://www.lrec-conf.org/proceedings/lrec2014/pdf/187_Paper.pdf) (Almeida et al., LREC 2014)
ACL