@inproceedings{mondary-etal-2012-quaero,
title = "The Quaero Evaluation Initiative on Term Extraction",
author = {Mondary, Thibault and
Nazarenko, Adeline and
Zargayouna, Ha{\"\i}fa and
Barreaux, Sabine},
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/812_Paper.pdf",
pages = "663--669",
abstract = "The Quaero program has organized a set of evaluations for terminology extraction systems in 2010 and 2011. Three objectives were targeted in this initiative: the first one was to evaluate the behavior and scalability of term extractors regarding the size of corpora, the second goal was to assess progress between different versions of the same systems, the last one was to measure the influence of corpus type. The protocol used during this initiative was a comparative analysis of 32 runs against a gold standard. Scores were computed using metrics that take into account gradual relevance. Systems produced by Quaero partners and publicly available systems were evaluated on pharmacology corpora composed of European Patents or abstracts of scientific articles, all in English. The gold standard was an unstructured version of the pharmacology thesaurus used by INIST-CNRS for indexing purposes. Most systems scaled with large corpora, contrasted differences were observed between different versions of the same systems and with better results on scientific articles than on patents. During the ongoing adjudication phase domain experts are enriching the thesaurus with terms found by several systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mondary-etal-2012-quaero">
<titleInfo>
<title>The Quaero Evaluation Initiative on Term Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thibault</namePart>
<namePart type="family">Mondary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adeline</namePart>
<namePart type="family">Nazarenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haïfa</namePart>
<namePart type="family">Zargayouna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabine</namePart>
<namePart type="family">Barreaux</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>The Quaero program has organized a set of evaluations for terminology extraction systems in 2010 and 2011. Three objectives were targeted in this initiative: the first one was to evaluate the behavior and scalability of term extractors regarding the size of corpora, the second goal was to assess progress between different versions of the same systems, the last one was to measure the influence of corpus type. The protocol used during this initiative was a comparative analysis of 32 runs against a gold standard. Scores were computed using metrics that take into account gradual relevance. Systems produced by Quaero partners and publicly available systems were evaluated on pharmacology corpora composed of European Patents or abstracts of scientific articles, all in English. The gold standard was an unstructured version of the pharmacology thesaurus used by INIST-CNRS for indexing purposes. Most systems scaled with large corpora, contrasted differences were observed between different versions of the same systems and with better results on scientific articles than on patents. During the ongoing adjudication phase domain experts are enriching the thesaurus with terms found by several systems.</abstract>
<identifier type="citekey">mondary-etal-2012-quaero</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/812_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>663</start>
<end>669</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Quaero Evaluation Initiative on Term Extraction
%A Mondary, Thibault
%A Nazarenko, Adeline
%A Zargayouna, Haïfa
%A Barreaux, Sabine
%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 mondary-etal-2012-quaero
%X The Quaero program has organized a set of evaluations for terminology extraction systems in 2010 and 2011. Three objectives were targeted in this initiative: the first one was to evaluate the behavior and scalability of term extractors regarding the size of corpora, the second goal was to assess progress between different versions of the same systems, the last one was to measure the influence of corpus type. The protocol used during this initiative was a comparative analysis of 32 runs against a gold standard. Scores were computed using metrics that take into account gradual relevance. Systems produced by Quaero partners and publicly available systems were evaluated on pharmacology corpora composed of European Patents or abstracts of scientific articles, all in English. The gold standard was an unstructured version of the pharmacology thesaurus used by INIST-CNRS for indexing purposes. Most systems scaled with large corpora, contrasted differences were observed between different versions of the same systems and with better results on scientific articles than on patents. During the ongoing adjudication phase domain experts are enriching the thesaurus with terms found by several systems.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/812_Paper.pdf
%P 663-669
Markdown (Informal)
[The Quaero Evaluation Initiative on Term Extraction](http://www.lrec-conf.org/proceedings/lrec2012/pdf/812_Paper.pdf) (Mondary et al., LREC 2012)
ACL
- Thibault Mondary, Adeline Nazarenko, Haïfa Zargayouna, and Sabine Barreaux. 2012. The Quaero Evaluation Initiative on Term Extraction. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 663–669, Istanbul, Turkey. European Language Resources Association (ELRA).