@inproceedings{weller-heid-2010-extraction,
title = "Extraction of {G}erman Multiword Expressions from Parsed Corpora Using Context Features",
author = "Weller, Marion and
Heid, Ulrich",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/428_Paper.pdf",
abstract = "We report about tools for the extraction of German multiword expressions (MWEs) from text corpora; we extract word pairs, but also longer MWEs of different patterns, e.g. verb-noun structures with an additional prepositional phrase or adjective. Next to standard association-based extraction, we focus on morpho-syntactic, syntactic and lexical-choice features of the MWE candidates. A broad range of such properties (e.g. number and definiteness of nouns, adjacency of the MWEs components and their position in the sentence, preferred lexical modifiers, etc.) along with relevant example sentences, are extracted from dependency-parsed text and stored in a data base. A sample precision evaluation and an analysis of extraction errors are provided along with the discussion of our extraction architecture. We furthermore measure the contribution of the features to the precision of the extraction: by using both morpho-syntactic and syntactic features, we achieve a higher precision in the identification of idiomatic MWEs, than by using only properties of one type.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="weller-heid-2010-extraction">
<titleInfo>
<title>Extraction of German Multiword Expressions from Parsed Corpora Using Context Features</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marion</namePart>
<namePart type="family">Weller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ulrich</namePart>
<namePart type="family">Heid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">Mike</namePart>
<namePart type="family">Rosner</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">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We report about tools for the extraction of German multiword expressions (MWEs) from text corpora; we extract word pairs, but also longer MWEs of different patterns, e.g. verb-noun structures with an additional prepositional phrase or adjective. Next to standard association-based extraction, we focus on morpho-syntactic, syntactic and lexical-choice features of the MWE candidates. A broad range of such properties (e.g. number and definiteness of nouns, adjacency of the MWEs components and their position in the sentence, preferred lexical modifiers, etc.) along with relevant example sentences, are extracted from dependency-parsed text and stored in a data base. A sample precision evaluation and an analysis of extraction errors are provided along with the discussion of our extraction architecture. We furthermore measure the contribution of the features to the precision of the extraction: by using both morpho-syntactic and syntactic features, we achieve a higher precision in the identification of idiomatic MWEs, than by using only properties of one type.</abstract>
<identifier type="citekey">weller-heid-2010-extraction</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/428_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extraction of German Multiword Expressions from Parsed Corpora Using Context Features
%A Weller, Marion
%A Heid, Ulrich
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F weller-heid-2010-extraction
%X We report about tools for the extraction of German multiword expressions (MWEs) from text corpora; we extract word pairs, but also longer MWEs of different patterns, e.g. verb-noun structures with an additional prepositional phrase or adjective. Next to standard association-based extraction, we focus on morpho-syntactic, syntactic and lexical-choice features of the MWE candidates. A broad range of such properties (e.g. number and definiteness of nouns, adjacency of the MWEs components and their position in the sentence, preferred lexical modifiers, etc.) along with relevant example sentences, are extracted from dependency-parsed text and stored in a data base. A sample precision evaluation and an analysis of extraction errors are provided along with the discussion of our extraction architecture. We furthermore measure the contribution of the features to the precision of the extraction: by using both morpho-syntactic and syntactic features, we achieve a higher precision in the identification of idiomatic MWEs, than by using only properties of one type.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/428_Paper.pdf
Markdown (Informal)
[Extraction of German Multiword Expressions from Parsed Corpora Using Context Features](http://www.lrec-conf.org/proceedings/lrec2010/pdf/428_Paper.pdf) (Weller & Heid, LREC 2010)
ACL