@inproceedings{kilgarriff-etal-2014-extrinsic,
title = "Extrinsic Corpus Evaluation with a Collocation Dictionary Task",
author = "Kilgarriff, Adam and
Rychl{\'y}, Pavel and
Jakub{\'\i}{\v{c}}ek, Milo{\v{s}} and
Kov{\'a}{\v{r}}, Vojt{\v{e}}ch and
Baisa, V{\'\i}t and
Kocincov{\'a}, Lucia",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/52_Paper.pdf",
pages = "545--552",
abstract = "The NLP researcher or application-builder often wonders {``}what corpus should I use, or should I build one of my own? If I build one of my own, how will I know if I have done a good job?{''} Currently there is very little help available for them. They are in need of a framework for evaluating corpora. We develop such a framework, in relation to corpora which aim for good coverage of {`}general language{'}. The task we set is automatic creation of a publication-quality collocations dictionary. For a sample of 100 headwords of Czech and 100 of English, we identify a gold standard dataset of (ideally) all the collocations that should appear for these headwords in such a dictionary. The datasets are being made available alongside this paper. We then use them to determine precision and recall for a range of corpora, with a range of parameters.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kilgarriff-etal-2014-extrinsic">
<titleInfo>
<title>Extrinsic Corpus Evaluation with a Collocation Dictionary Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Kilgarriff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Rychlý</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miloš</namePart>
<namePart type="family">Jakubíček</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vojtěch</namePart>
<namePart type="family">Kovář</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vít</namePart>
<namePart type="family">Baisa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Kocincová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The NLP researcher or application-builder often wonders “what corpus should I use, or should I build one of my own? If I build one of my own, how will I know if I have done a good job?” Currently there is very little help available for them. They are in need of a framework for evaluating corpora. We develop such a framework, in relation to corpora which aim for good coverage of ‘general language’. The task we set is automatic creation of a publication-quality collocations dictionary. For a sample of 100 headwords of Czech and 100 of English, we identify a gold standard dataset of (ideally) all the collocations that should appear for these headwords in such a dictionary. The datasets are being made available alongside this paper. We then use them to determine precision and recall for a range of corpora, with a range of parameters.</abstract>
<identifier type="citekey">kilgarriff-etal-2014-extrinsic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/52_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>545</start>
<end>552</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extrinsic Corpus Evaluation with a Collocation Dictionary Task
%A Kilgarriff, Adam
%A Rychlý, Pavel
%A Jakubíček, Miloš
%A Kovář, Vojtěch
%A Baisa, Vít
%A Kocincová, Lucia
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F kilgarriff-etal-2014-extrinsic
%X The NLP researcher or application-builder often wonders “what corpus should I use, or should I build one of my own? If I build one of my own, how will I know if I have done a good job?” Currently there is very little help available for them. They are in need of a framework for evaluating corpora. We develop such a framework, in relation to corpora which aim for good coverage of ‘general language’. The task we set is automatic creation of a publication-quality collocations dictionary. For a sample of 100 headwords of Czech and 100 of English, we identify a gold standard dataset of (ideally) all the collocations that should appear for these headwords in such a dictionary. The datasets are being made available alongside this paper. We then use them to determine precision and recall for a range of corpora, with a range of parameters.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/52_Paper.pdf
%P 545-552
Markdown (Informal)
[Extrinsic Corpus Evaluation with a Collocation Dictionary Task](http://www.lrec-conf.org/proceedings/lrec2014/pdf/52_Paper.pdf) (Kilgarriff et al., LREC 2014)
ACL
- Adam Kilgarriff, Pavel Rychlý, Miloš Jakubíček, Vojtěch Kovář, Vít Baisa, and Lucia Kocincová. 2014. Extrinsic Corpus Evaluation with a Collocation Dictionary Task. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 545–552, Reykjavik, Iceland. European Language Resources Association (ELRA).