@inproceedings{galibert-etal-2012-extended,
title = "Extended Named Entities Annotation on {OCR}ed Documents: From Corpus Constitution to Evaluation Campaign",
author = "Galibert, Olivier and
Rosset, Sophie and
Grouin, Cyril and
Zweigenbaum, Pierre and
Quintard, Ludovic",
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/343_Paper.pdf",
pages = "3126--3131",
abstract = "Within the framework of the Quaero project, we proposed a new definition of named entities, based upon an extension of the coverage of named entities as well as the structure of those named entities. In this new definition, the extended named entities we proposed are both hierarchical and compositional. In this paper, we focused on the annotation of a corpus composed of press archives, OCRed from French newspapers of December 1890. We present the methodology we used to produce the corpus and the characteristics of the corpus in terms of named entities annotation. This annotated corpus has been used in an evaluation campaign. We present this evaluation, the metrics we used and the results obtained by the participants.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="galibert-etal-2012-extended">
<titleInfo>
<title>Extended Named Entities Annotation on OCRed Documents: From Corpus Constitution to Evaluation Campaign</title>
</titleInfo>
<name type="personal">
<namePart type="given">Olivier</namePart>
<namePart type="family">Galibert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophie</namePart>
<namePart type="family">Rosset</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cyril</namePart>
<namePart type="family">Grouin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Zweigenbaum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ludovic</namePart>
<namePart type="family">Quintard</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>Within the framework of the Quaero project, we proposed a new definition of named entities, based upon an extension of the coverage of named entities as well as the structure of those named entities. In this new definition, the extended named entities we proposed are both hierarchical and compositional. In this paper, we focused on the annotation of a corpus composed of press archives, OCRed from French newspapers of December 1890. We present the methodology we used to produce the corpus and the characteristics of the corpus in terms of named entities annotation. This annotated corpus has been used in an evaluation campaign. We present this evaluation, the metrics we used and the results obtained by the participants.</abstract>
<identifier type="citekey">galibert-etal-2012-extended</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/343_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3126</start>
<end>3131</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extended Named Entities Annotation on OCRed Documents: From Corpus Constitution to Evaluation Campaign
%A Galibert, Olivier
%A Rosset, Sophie
%A Grouin, Cyril
%A Zweigenbaum, Pierre
%A Quintard, Ludovic
%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 galibert-etal-2012-extended
%X Within the framework of the Quaero project, we proposed a new definition of named entities, based upon an extension of the coverage of named entities as well as the structure of those named entities. In this new definition, the extended named entities we proposed are both hierarchical and compositional. In this paper, we focused on the annotation of a corpus composed of press archives, OCRed from French newspapers of December 1890. We present the methodology we used to produce the corpus and the characteristics of the corpus in terms of named entities annotation. This annotated corpus has been used in an evaluation campaign. We present this evaluation, the metrics we used and the results obtained by the participants.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/343_Paper.pdf
%P 3126-3131
Markdown (Informal)
[Extended Named Entities Annotation on OCRed Documents: From Corpus Constitution to Evaluation Campaign](http://www.lrec-conf.org/proceedings/lrec2012/pdf/343_Paper.pdf) (Galibert et al., LREC 2012)
ACL