@inproceedings{ljubesic-etal-2010-building,
title = "Building a Gold Standard for Event Detection in {C}roatian",
author = "Ljube{\v{s}}i{\'c}, Nikola and
Lauc, Tomislava and
Boras, Damir",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/213_Paper.pdf",
abstract = "This paper describes the process of building a newspaper corpus annotated with events described in specific documents. The main difference to the corpora built as part of the TDT initiative is that documents are not annotated by topics, but by specific events they describe. Additionally, documents are gathered from sixteen sources and all documents in the corpus are annotated with the corresponding event. The annotation process consists of a browsing and a searching step. Experiments are performed with a threshold that could be used in the browsing step yielding the result of having to browse through only 1{\%} of document pairs for a 2{\%} loss of relevant document pairs. A statistical analysis of the annotated corpus is undertaken showing that most events are described by few documents while just some events are reported by many documents. The inter-annotator agreement measures show high agreement concerning grouping documents into event clusters, but show a much lower agreement concerning the number of events the documents are organized into. An initial experiment is described giving a baseline for further research on this corpus.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ljubesic-etal-2010-building">
<titleInfo>
<title>Building a Gold Standard for Event Detection in Croatian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomislava</namePart>
<namePart type="family">Lauc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damir</namePart>
<namePart type="family">Boras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">Mike</namePart>
<namePart type="family">Rosner</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">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the process of building a newspaper corpus annotated with events described in specific documents. The main difference to the corpora built as part of the TDT initiative is that documents are not annotated by topics, but by specific events they describe. Additionally, documents are gathered from sixteen sources and all documents in the corpus are annotated with the corresponding event. The annotation process consists of a browsing and a searching step. Experiments are performed with a threshold that could be used in the browsing step yielding the result of having to browse through only 1% of document pairs for a 2% loss of relevant document pairs. A statistical analysis of the annotated corpus is undertaken showing that most events are described by few documents while just some events are reported by many documents. The inter-annotator agreement measures show high agreement concerning grouping documents into event clusters, but show a much lower agreement concerning the number of events the documents are organized into. An initial experiment is described giving a baseline for further research on this corpus.</abstract>
<identifier type="citekey">ljubesic-etal-2010-building</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/213_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building a Gold Standard for Event Detection in Croatian
%A Ljubešić, Nikola
%A Lauc, Tomislava
%A Boras, Damir
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F ljubesic-etal-2010-building
%X This paper describes the process of building a newspaper corpus annotated with events described in specific documents. The main difference to the corpora built as part of the TDT initiative is that documents are not annotated by topics, but by specific events they describe. Additionally, documents are gathered from sixteen sources and all documents in the corpus are annotated with the corresponding event. The annotation process consists of a browsing and a searching step. Experiments are performed with a threshold that could be used in the browsing step yielding the result of having to browse through only 1% of document pairs for a 2% loss of relevant document pairs. A statistical analysis of the annotated corpus is undertaken showing that most events are described by few documents while just some events are reported by many documents. The inter-annotator agreement measures show high agreement concerning grouping documents into event clusters, but show a much lower agreement concerning the number of events the documents are organized into. An initial experiment is described giving a baseline for further research on this corpus.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/213_Paper.pdf
Markdown (Informal)
[Building a Gold Standard for Event Detection in Croatian](http://www.lrec-conf.org/proceedings/lrec2010/pdf/213_Paper.pdf) (Ljubešić et al., LREC 2010)
ACL
- Nikola Ljubešić, Tomislava Lauc, and Damir Boras. 2010. Building a Gold Standard for Event Detection in Croatian. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).