@inproceedings{vaneyghen-etal-2006-mixed,
title = "A mixed word / morphological approach for extending {CELEX} for high coverage on contemporary large corpora",
author = "Vaneyghen, Joris and
De Pauw, Guy and
Van Compernolle, Dirk and
Daelemans, Walter",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/583_pdf.pdf",
abstract = "This paper describes an alternative approach to morphological language modeling, which incorporates constraints on the morphological production of new words. This is done by applying the constraints as a preprocessing step in which only one morphological production rule can be applied to an extended lexicon of knownmorphemes, lemmas and word forms. This approach is used to extend the CELEX Dutch morphological database, so that a higher coverage can be reached on a largecorpus of Dutch newspaper articles. We present experimental results on the coverage of this extended database and use the extension to further evaluate our morphologicalsystem, as well as the impact of the constraints on the coverage of out-of-vocabulary words.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vaneyghen-etal-2006-mixed">
<titleInfo>
<title>A mixed word / morphological approach for extending CELEX for high coverage on contemporary large corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joris</namePart>
<namePart type="family">Vaneyghen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">De Pauw</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dirk</namePart>
<namePart type="family">Van Compernolle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walter</namePart>
<namePart type="family">Daelemans</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">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">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes an alternative approach to morphological language modeling, which incorporates constraints on the morphological production of new words. This is done by applying the constraints as a preprocessing step in which only one morphological production rule can be applied to an extended lexicon of knownmorphemes, lemmas and word forms. This approach is used to extend the CELEX Dutch morphological database, so that a higher coverage can be reached on a largecorpus of Dutch newspaper articles. We present experimental results on the coverage of this extended database and use the extension to further evaluate our morphologicalsystem, as well as the impact of the constraints on the coverage of out-of-vocabulary words.</abstract>
<identifier type="citekey">vaneyghen-etal-2006-mixed</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/583_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A mixed word / morphological approach for extending CELEX for high coverage on contemporary large corpora
%A Vaneyghen, Joris
%A De Pauw, Guy
%A Van Compernolle, Dirk
%A Daelemans, Walter
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F vaneyghen-etal-2006-mixed
%X This paper describes an alternative approach to morphological language modeling, which incorporates constraints on the morphological production of new words. This is done by applying the constraints as a preprocessing step in which only one morphological production rule can be applied to an extended lexicon of knownmorphemes, lemmas and word forms. This approach is used to extend the CELEX Dutch morphological database, so that a higher coverage can be reached on a largecorpus of Dutch newspaper articles. We present experimental results on the coverage of this extended database and use the extension to further evaluate our morphologicalsystem, as well as the impact of the constraints on the coverage of out-of-vocabulary words.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/583_pdf.pdf
Markdown (Informal)
[A mixed word / morphological approach for extending CELEX for high coverage on contemporary large corpora](http://www.lrec-conf.org/proceedings/lrec2006/pdf/583_pdf.pdf) (Vaneyghen et al., LREC 2006)
ACL