@inproceedings{saggion-szasz-2012-concisus,
title = "The {CONCISUS} Corpus of Event Summaries",
author = "Saggion, Horacio and
Szasz, Sandra",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/642_Paper.pdf",
pages = "2031--2037",
abstract = "Text summarization and information extraction systems require adaptation to new domains and languages. This adaptation usually depends on the availability of language resources such as corpora. In this paper we present a comparable corpus in Spanish and English for the study of cross-lingual information extraction and summarization: the CONCISUS Corpus. It is a rich human-annotated dataset composed of comparable event summaries in Spanish and English covering four different domains: aviation accidents, rail accidents, earthquakes, and terrorist attacks. In addition to the monolingual summaries in English and Spanish, we provide automatic translations and ``comparable'' full event reports of the events. The human annotations are concepts marked in the textual sources representing the key event information associated to the event type. The dataset has also been annotated using text processing pipelines. It is being made freely available to the research community for research purposes.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saggion-szasz-2012-concisus">
<titleInfo>
<title>The CONCISUS Corpus of Event Summaries</title>
</titleInfo>
<name type="personal">
<namePart type="given">Horacio</namePart>
<namePart type="family">Saggion</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="family">Szasz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Text summarization and information extraction systems require adaptation to new domains and languages. This adaptation usually depends on the availability of language resources such as corpora. In this paper we present a comparable corpus in Spanish and English for the study of cross-lingual information extraction and summarization: the CONCISUS Corpus. It is a rich human-annotated dataset composed of comparable event summaries in Spanish and English covering four different domains: aviation accidents, rail accidents, earthquakes, and terrorist attacks. In addition to the monolingual summaries in English and Spanish, we provide automatic translations and “comparable” full event reports of the events. The human annotations are concepts marked in the textual sources representing the key event information associated to the event type. The dataset has also been annotated using text processing pipelines. It is being made freely available to the research community for research purposes.</abstract>
<identifier type="citekey">saggion-szasz-2012-concisus</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/642_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2031</start>
<end>2037</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The CONCISUS Corpus of Event Summaries
%A Saggion, Horacio
%A Szasz, Sandra
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F saggion-szasz-2012-concisus
%X Text summarization and information extraction systems require adaptation to new domains and languages. This adaptation usually depends on the availability of language resources such as corpora. In this paper we present a comparable corpus in Spanish and English for the study of cross-lingual information extraction and summarization: the CONCISUS Corpus. It is a rich human-annotated dataset composed of comparable event summaries in Spanish and English covering four different domains: aviation accidents, rail accidents, earthquakes, and terrorist attacks. In addition to the monolingual summaries in English and Spanish, we provide automatic translations and “comparable” full event reports of the events. The human annotations are concepts marked in the textual sources representing the key event information associated to the event type. The dataset has also been annotated using text processing pipelines. It is being made freely available to the research community for research purposes.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/642_Paper.pdf
%P 2031-2037
Markdown (Informal)
[The CONCISUS Corpus of Event Summaries](http://www.lrec-conf.org/proceedings/lrec2012/pdf/642_Paper.pdf) (Saggion & Szasz, LREC 2012)
ACL
- Horacio Saggion and Sandra Szasz. 2012. The CONCISUS Corpus of Event Summaries. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2031–2037, Istanbul, Turkey. European Language Resources Association (ELRA).