@inproceedings{sagot-stern-2012-aleda,
title = "Aleda, a free large-scale entity database for {F}rench",
author = "Sagot, Beno{\^\i}t and
Stern, Rosa",
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/1124_Paper.pdf",
pages = "1273--1276",
abstract = "Named entity recognition, which focuses on the identification of the span and type of named entity mentions in texts, has drawn the attention of the NLP community for a long time. However, many real-life applications need to know which real entity each mention refers to. For such a purpose, often refered to as entity resolution and linking, an inventory of entities is required in order to constitute a reference. In this paper, we describe how we extracted such a resource for French from freely available resources (the French Wikipedia and the GeoNames database). We describe the results of an instrinsic evaluation of the resulting entity database, named Aleda, as well as those of a task-based evaluation in the context of a named entity detection system. We also compare it with the NLGbAse database (Charton and Torres-Moreno, 2010), a resource with similar objectives.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sagot-stern-2012-aleda">
<titleInfo>
<title>Aleda, a free large-scale entity database for French</title>
</titleInfo>
<name type="personal">
<namePart type="given">Benoît</namePart>
<namePart type="family">Sagot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rosa</namePart>
<namePart type="family">Stern</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>Named entity recognition, which focuses on the identification of the span and type of named entity mentions in texts, has drawn the attention of the NLP community for a long time. However, many real-life applications need to know which real entity each mention refers to. For such a purpose, often refered to as entity resolution and linking, an inventory of entities is required in order to constitute a reference. In this paper, we describe how we extracted such a resource for French from freely available resources (the French Wikipedia and the GeoNames database). We describe the results of an instrinsic evaluation of the resulting entity database, named Aleda, as well as those of a task-based evaluation in the context of a named entity detection system. We also compare it with the NLGbAse database (Charton and Torres-Moreno, 2010), a resource with similar objectives.</abstract>
<identifier type="citekey">sagot-stern-2012-aleda</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/1124_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>1273</start>
<end>1276</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Aleda, a free large-scale entity database for French
%A Sagot, Benoît
%A Stern, Rosa
%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 sagot-stern-2012-aleda
%X Named entity recognition, which focuses on the identification of the span and type of named entity mentions in texts, has drawn the attention of the NLP community for a long time. However, many real-life applications need to know which real entity each mention refers to. For such a purpose, often refered to as entity resolution and linking, an inventory of entities is required in order to constitute a reference. In this paper, we describe how we extracted such a resource for French from freely available resources (the French Wikipedia and the GeoNames database). We describe the results of an instrinsic evaluation of the resulting entity database, named Aleda, as well as those of a task-based evaluation in the context of a named entity detection system. We also compare it with the NLGbAse database (Charton and Torres-Moreno, 2010), a resource with similar objectives.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/1124_Paper.pdf
%P 1273-1276
Markdown (Informal)
[Aleda, a free large-scale entity database for French](http://www.lrec-conf.org/proceedings/lrec2012/pdf/1124_Paper.pdf) (Sagot & Stern, LREC 2012)
ACL
- Benoît Sagot and Rosa Stern. 2012. Aleda, a free large-scale entity database for French. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 1273–1276, Istanbul, Turkey. European Language Resources Association (ELRA).