@inproceedings{vintar-fiser-2008-harvesting,
title = "Harvesting Multi-Word Expressions from Parallel Corpora",
author = "Vintar, {\v{S}}pela and
Fi{\v{s}}er, Darja",
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/281_paper.pdf",
abstract = "The paper presents a set of approaches to extend the automatically created Slovene wordnet with nominal multi-word expressions. In the first approach multi-word expressions from Princeton WordNet are translated with a technique that is based on word-alignment and lexico-syntactic patterns. This is followed by extracting new terms from a monolingual corpus using keywordness ranking and contextual patterns. Finally, the multi-word expressions are assigned a hypernym and added to our wordnet. Manual evaluation and comparison of the results shows that the translation approach is the most straightforward and accurate. However, it is successfully complemented by the two monolingual approaches which are able to identify more term candidates in the corpus that would otherwise go unnoticed. Some weaknesses of the proposed wordnet extension techniques are also addressed.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vintar-fiser-2008-harvesting">
<titleInfo>
<title>Harvesting Multi-Word Expressions from Parallel Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Špela</namePart>
<namePart type="family">Vintar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Darja</namePart>
<namePart type="family">Fišer</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>The paper presents a set of approaches to extend the automatically created Slovene wordnet with nominal multi-word expressions. In the first approach multi-word expressions from Princeton WordNet are translated with a technique that is based on word-alignment and lexico-syntactic patterns. This is followed by extracting new terms from a monolingual corpus using keywordness ranking and contextual patterns. Finally, the multi-word expressions are assigned a hypernym and added to our wordnet. Manual evaluation and comparison of the results shows that the translation approach is the most straightforward and accurate. However, it is successfully complemented by the two monolingual approaches which are able to identify more term candidates in the corpus that would otherwise go unnoticed. Some weaknesses of the proposed wordnet extension techniques are also addressed.</abstract>
<identifier type="citekey">vintar-fiser-2008-harvesting</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/281_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Harvesting Multi-Word Expressions from Parallel Corpora
%A Vintar, Špela
%A Fišer, Darja
%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 vintar-fiser-2008-harvesting
%X The paper presents a set of approaches to extend the automatically created Slovene wordnet with nominal multi-word expressions. In the first approach multi-word expressions from Princeton WordNet are translated with a technique that is based on word-alignment and lexico-syntactic patterns. This is followed by extracting new terms from a monolingual corpus using keywordness ranking and contextual patterns. Finally, the multi-word expressions are assigned a hypernym and added to our wordnet. Manual evaluation and comparison of the results shows that the translation approach is the most straightforward and accurate. However, it is successfully complemented by the two monolingual approaches which are able to identify more term candidates in the corpus that would otherwise go unnoticed. Some weaknesses of the proposed wordnet extension techniques are also addressed.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/281_paper.pdf
Markdown (Informal)
[Harvesting Multi-Word Expressions from Parallel Corpora](http://www.lrec-conf.org/proceedings/lrec2008/pdf/281_paper.pdf) (Vintar & Fišer, LREC 2008)
ACL