@inproceedings{caselli-etal-2012-customizable,
title = "Customizable {SCF} Acquisition in {I}talian",
author = "Caselli, Tommaso and
Rubino, Francesco and
Frontini, Francesca and
Russo, Irene and
Quochi, Valeria",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/390_Paper.pdf",
pages = "2842--2848",
abstract = "Lexica of predicate-argument structures constitute a useful tool for several tasks in NLP. This paper describes a web-service system for automatic acquisition of verb subcategorization frames (SCFs) from parsed data in Italian. The system acquires SCFs in an unsupervised manner. We created two gold standards for the evaluation of the system, the first by mixing together information from two lexica (one manually created and the second automatically acquired) and manual exploration of corpus data and the other annotating data extracted from a specialized corpus (environmental domain). Data filtering is accomplished by means of the maximum likelihood estimate (MLE). The evaluation phase has allowed us to identify the best empirical MLE threshold for the creation of a lexicon (P=0.653, R=0.557, F1=0.601). In addition to this, we assigned to the extracted entries of the lexicon a confidence score based on the relative frequency and evaluated the extractor on domain specific data. The confidence score will allow the final user to easily select the entries of the lexicon in terms of their reliability: one of the most interesting feature of this work is the possibility the final users have to customize the results of the SCF extractor, obtaining different SCF lexica in terms of size and accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="caselli-etal-2012-customizable">
<titleInfo>
<title>Customizable SCF Acquisition in Italian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tommaso</namePart>
<namePart type="family">Caselli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francesco</namePart>
<namePart type="family">Rubino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francesca</namePart>
<namePart type="family">Frontini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Irene</namePart>
<namePart type="family">Russo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valeria</namePart>
<namePart type="family">Quochi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Asuncion</namePart>
<namePart type="family">Moreno</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>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Lexica of predicate-argument structures constitute a useful tool for several tasks in NLP. This paper describes a web-service system for automatic acquisition of verb subcategorization frames (SCFs) from parsed data in Italian. The system acquires SCFs in an unsupervised manner. We created two gold standards for the evaluation of the system, the first by mixing together information from two lexica (one manually created and the second automatically acquired) and manual exploration of corpus data and the other annotating data extracted from a specialized corpus (environmental domain). Data filtering is accomplished by means of the maximum likelihood estimate (MLE). The evaluation phase has allowed us to identify the best empirical MLE threshold for the creation of a lexicon (P=0.653, R=0.557, F1=0.601). In addition to this, we assigned to the extracted entries of the lexicon a confidence score based on the relative frequency and evaluated the extractor on domain specific data. The confidence score will allow the final user to easily select the entries of the lexicon in terms of their reliability: one of the most interesting feature of this work is the possibility the final users have to customize the results of the SCF extractor, obtaining different SCF lexica in terms of size and accuracy.</abstract>
<identifier type="citekey">caselli-etal-2012-customizable</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/390_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2842</start>
<end>2848</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Customizable SCF Acquisition in Italian
%A Caselli, Tommaso
%A Rubino, Francesco
%A Frontini, Francesca
%A Russo, Irene
%A Quochi, Valeria
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F caselli-etal-2012-customizable
%X Lexica of predicate-argument structures constitute a useful tool for several tasks in NLP. This paper describes a web-service system for automatic acquisition of verb subcategorization frames (SCFs) from parsed data in Italian. The system acquires SCFs in an unsupervised manner. We created two gold standards for the evaluation of the system, the first by mixing together information from two lexica (one manually created and the second automatically acquired) and manual exploration of corpus data and the other annotating data extracted from a specialized corpus (environmental domain). Data filtering is accomplished by means of the maximum likelihood estimate (MLE). The evaluation phase has allowed us to identify the best empirical MLE threshold for the creation of a lexicon (P=0.653, R=0.557, F1=0.601). In addition to this, we assigned to the extracted entries of the lexicon a confidence score based on the relative frequency and evaluated the extractor on domain specific data. The confidence score will allow the final user to easily select the entries of the lexicon in terms of their reliability: one of the most interesting feature of this work is the possibility the final users have to customize the results of the SCF extractor, obtaining different SCF lexica in terms of size and accuracy.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/390_Paper.pdf
%P 2842-2848
Markdown (Informal)
[Customizable SCF Acquisition in Italian](http://www.lrec-conf.org/proceedings/lrec2012/pdf/390_Paper.pdf) (Caselli et al., LREC 2012)
ACL
- Tommaso Caselli, Francesco Rubino, Francesca Frontini, Irene Russo, and Valeria Quochi. 2012. Customizable SCF Acquisition in Italian. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2842–2848, Istanbul, Turkey. European Language Resources Association (ELRA).