@inproceedings{banski-moszczynski-2008-enhancing,
title = "Enhancing an {E}nglish-{P}olish Electronic Dictionary for Multiword Expression Research",
author = "Ba{\'n}ski, Piotr and
Moszczy{\'n}ski, Rados{\l}aw",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/651_paper.pdf",
abstract = "This paper describes a project aimed at converting a legacy representation of English idioms into an XML-based format. The project is set in the context of a large electronic English-Polish dictionary which contains several hundred formalized idiom descriptions and which has been released under the terms of a free license. In short, the project consists of three phases: cleaning up the dictionary markup, extracting the legacy idiom representations, and converting them into TEI P5 XML constrained by a RelaxNG grammar created for this purpose and constituting a module that can be included as part of the TEI P5 schema. The paper contains general descriptions of the individual phases and several examples of XML-encoded idioms. It also suggests some directions for further research, which include abstracting the XML-ized idiom representations into general syntactic patterns and using the representations to automatically identify idioms in tagged corpora.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="banski-moszczynski-2008-enhancing">
<titleInfo>
<title>Enhancing an English-Polish Electronic Dictionary for Multiword Expression Research</title>
</titleInfo>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Bański</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Radosław</namePart>
<namePart type="family">Moszczyński</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Stelios</namePart>
<namePart type="family">Piperidis</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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes a project aimed at converting a legacy representation of English idioms into an XML-based format. The project is set in the context of a large electronic English-Polish dictionary which contains several hundred formalized idiom descriptions and which has been released under the terms of a free license. In short, the project consists of three phases: cleaning up the dictionary markup, extracting the legacy idiom representations, and converting them into TEI P5 XML constrained by a RelaxNG grammar created for this purpose and constituting a module that can be included as part of the TEI P5 schema. The paper contains general descriptions of the individual phases and several examples of XML-encoded idioms. It also suggests some directions for further research, which include abstracting the XML-ized idiom representations into general syntactic patterns and using the representations to automatically identify idioms in tagged corpora.</abstract>
<identifier type="citekey">banski-moszczynski-2008-enhancing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/651_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing an English-Polish Electronic Dictionary for Multiword Expression Research
%A Bański, Piotr
%A Moszczyński, Radosław
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F banski-moszczynski-2008-enhancing
%X This paper describes a project aimed at converting a legacy representation of English idioms into an XML-based format. The project is set in the context of a large electronic English-Polish dictionary which contains several hundred formalized idiom descriptions and which has been released under the terms of a free license. In short, the project consists of three phases: cleaning up the dictionary markup, extracting the legacy idiom representations, and converting them into TEI P5 XML constrained by a RelaxNG grammar created for this purpose and constituting a module that can be included as part of the TEI P5 schema. The paper contains general descriptions of the individual phases and several examples of XML-encoded idioms. It also suggests some directions for further research, which include abstracting the XML-ized idiom representations into general syntactic patterns and using the representations to automatically identify idioms in tagged corpora.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/651_paper.pdf
Markdown (Informal)
[Enhancing an English-Polish Electronic Dictionary for Multiword Expression Research](http://www.lrec-conf.org/proceedings/lrec2008/pdf/651_paper.pdf) (Bański & Moszczyński, LREC 2008)
ACL