@inproceedings{heid-weller-2008-tools,
title = "Tools for Collocation Extraction: Preferences for Active vs. Passive",
author = "Heid, Ulrich and
Weller, Marion",
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/323_paper.pdf",
abstract = "We present and partially evaluate procedures for the extraction of noun+verb collocation candidates from German text corpora, along with their morphosyntactic preferences, especially for the active vs. passive voice. We start from tokenized, tagged, lemmatized and chunked text, and we use extraction patterns formulated in the CQP corpus query language. We discuss the results of a precision evaluation, on administrative texts from the European Union: we find a considerable amount of specialized collocations, as well as general ones and complex predicates; overall the precision is considerably higher than that of a statistical extractor used as a baseline.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="heid-weller-2008-tools">
<titleInfo>
<title>Tools for Collocation Extraction: Preferences for Active vs. Passive</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ulrich</namePart>
<namePart type="family">Heid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marion</namePart>
<namePart type="family">Weller</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>We present and partially evaluate procedures for the extraction of noun+verb collocation candidates from German text corpora, along with their morphosyntactic preferences, especially for the active vs. passive voice. We start from tokenized, tagged, lemmatized and chunked text, and we use extraction patterns formulated in the CQP corpus query language. We discuss the results of a precision evaluation, on administrative texts from the European Union: we find a considerable amount of specialized collocations, as well as general ones and complex predicates; overall the precision is considerably higher than that of a statistical extractor used as a baseline.</abstract>
<identifier type="citekey">heid-weller-2008-tools</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/323_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tools for Collocation Extraction: Preferences for Active vs. Passive
%A Heid, Ulrich
%A Weller, Marion
%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 heid-weller-2008-tools
%X We present and partially evaluate procedures for the extraction of noun+verb collocation candidates from German text corpora, along with their morphosyntactic preferences, especially for the active vs. passive voice. We start from tokenized, tagged, lemmatized and chunked text, and we use extraction patterns formulated in the CQP corpus query language. We discuss the results of a precision evaluation, on administrative texts from the European Union: we find a considerable amount of specialized collocations, as well as general ones and complex predicates; overall the precision is considerably higher than that of a statistical extractor used as a baseline.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/323_paper.pdf
Markdown (Informal)
[Tools for Collocation Extraction: Preferences for Active vs. Passive](http://www.lrec-conf.org/proceedings/lrec2008/pdf/323_paper.pdf) (Heid & Weller, LREC 2008)
ACL