@inproceedings{chesley-salmon-alt-2006-automatic,
title = "Automatic extraction of subcategorization frames for {F}rench",
author = "Chesley, Paula and
Salmon-Alt, Susanne",
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/101_pdf.pdf",
abstract = "This paper describes the automatic extraction of French subcategorization frames from corpora. The subcategorization frames have been acquired via VISL, a dependency-based parser (Bick 2003), whose verb lexicon is currently incomplete with respect to subcategorization frames. Therefore, we have implemented binomial hypothesis testing as a post-parsing filtering step. On a test set of 104 frequent verbs we achieve lower bounds on type precision at 86.8{\%} and on token recall at 54.3{\%}. These results show that, contra (Korhonen et al. 2000), binomial hypothesis testing can be robust for determining subcategorization frames given corpus data. Additionally, we estimate that our extracted subcategorization frames account for 85.4{\%} of all frames in French corpora. We conclude that using a language resource, such as the VISL parser, with a currently unevaluated (and potentially high) error rate can yield robust results in conjunction with probabilistic filtering of the resource output.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chesley-salmon-alt-2006-automatic">
<titleInfo>
<title>Automatic extraction of subcategorization frames for French</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paula</namePart>
<namePart type="family">Chesley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Susanne</namePart>
<namePart type="family">Salmon-Alt</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 the automatic extraction of French subcategorization frames from corpora. The subcategorization frames have been acquired via VISL, a dependency-based parser (Bick 2003), whose verb lexicon is currently incomplete with respect to subcategorization frames. Therefore, we have implemented binomial hypothesis testing as a post-parsing filtering step. On a test set of 104 frequent verbs we achieve lower bounds on type precision at 86.8% and on token recall at 54.3%. These results show that, contra (Korhonen et al. 2000), binomial hypothesis testing can be robust for determining subcategorization frames given corpus data. Additionally, we estimate that our extracted subcategorization frames account for 85.4% of all frames in French corpora. We conclude that using a language resource, such as the VISL parser, with a currently unevaluated (and potentially high) error rate can yield robust results in conjunction with probabilistic filtering of the resource output.</abstract>
<identifier type="citekey">chesley-salmon-alt-2006-automatic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/101_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic extraction of subcategorization frames for French
%A Chesley, Paula
%A Salmon-Alt, Susanne
%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 chesley-salmon-alt-2006-automatic
%X This paper describes the automatic extraction of French subcategorization frames from corpora. The subcategorization frames have been acquired via VISL, a dependency-based parser (Bick 2003), whose verb lexicon is currently incomplete with respect to subcategorization frames. Therefore, we have implemented binomial hypothesis testing as a post-parsing filtering step. On a test set of 104 frequent verbs we achieve lower bounds on type precision at 86.8% and on token recall at 54.3%. These results show that, contra (Korhonen et al. 2000), binomial hypothesis testing can be robust for determining subcategorization frames given corpus data. Additionally, we estimate that our extracted subcategorization frames account for 85.4% of all frames in French corpora. We conclude that using a language resource, such as the VISL parser, with a currently unevaluated (and potentially high) error rate can yield robust results in conjunction with probabilistic filtering of the resource output.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/101_pdf.pdf
Markdown (Informal)
[Automatic extraction of subcategorization frames for French](http://www.lrec-conf.org/proceedings/lrec2006/pdf/101_pdf.pdf) (Chesley & Salmon-Alt, LREC 2006)
ACL