@inproceedings{ienco-etal-2008-automatic,
title = "Automatic extraction of subcategorization frames for {I}talian",
author = "Ienco, Dino and
Villata, Serena and
Bosco, Cristina",
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/536_paper.pdf",
abstract = "Subcategorization is a kind of knowledge which can be considered as crucial in several NLP tasks, such as Information Extraction or parsing, but the collection of very large resources including subcategorization representation is difficult and time-consuming. Various experiences show that the automatic extraction can be a practical and reliable solution for acquiring such a kind of knowledge. The aim of this paper is to investigate the relationships between subcategorization frame extraction and the nature of data from which the frames have to be extracted, e.g. how much the task can be influenced by the richness/poorness of the annotation. Therefore, we present some experiments that apply statistical subcategorization extraction methods, known in literature, on an Italian treebank that exploits a rich set of dependency relations that can be annotated at different degrees of specificity. Benefiting from the availability of relation sets that implement different granularity in the representation of relations, we evaluate our results with reference to previous works in a cross-linguistic perspective.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ienco-etal-2008-automatic">
<titleInfo>
<title>Automatic extraction of subcategorization frames for Italian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dino</namePart>
<namePart type="family">Ienco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serena</namePart>
<namePart type="family">Villata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">Bosco</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>Subcategorization is a kind of knowledge which can be considered as crucial in several NLP tasks, such as Information Extraction or parsing, but the collection of very large resources including subcategorization representation is difficult and time-consuming. Various experiences show that the automatic extraction can be a practical and reliable solution for acquiring such a kind of knowledge. The aim of this paper is to investigate the relationships between subcategorization frame extraction and the nature of data from which the frames have to be extracted, e.g. how much the task can be influenced by the richness/poorness of the annotation. Therefore, we present some experiments that apply statistical subcategorization extraction methods, known in literature, on an Italian treebank that exploits a rich set of dependency relations that can be annotated at different degrees of specificity. Benefiting from the availability of relation sets that implement different granularity in the representation of relations, we evaluate our results with reference to previous works in a cross-linguistic perspective.</abstract>
<identifier type="citekey">ienco-etal-2008-automatic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/536_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic extraction of subcategorization frames for Italian
%A Ienco, Dino
%A Villata, Serena
%A Bosco, Cristina
%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 ienco-etal-2008-automatic
%X Subcategorization is a kind of knowledge which can be considered as crucial in several NLP tasks, such as Information Extraction or parsing, but the collection of very large resources including subcategorization representation is difficult and time-consuming. Various experiences show that the automatic extraction can be a practical and reliable solution for acquiring such a kind of knowledge. The aim of this paper is to investigate the relationships between subcategorization frame extraction and the nature of data from which the frames have to be extracted, e.g. how much the task can be influenced by the richness/poorness of the annotation. Therefore, we present some experiments that apply statistical subcategorization extraction methods, known in literature, on an Italian treebank that exploits a rich set of dependency relations that can be annotated at different degrees of specificity. Benefiting from the availability of relation sets that implement different granularity in the representation of relations, we evaluate our results with reference to previous works in a cross-linguistic perspective.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/536_paper.pdf
Markdown (Informal)
[Automatic extraction of subcategorization frames for Italian](http://www.lrec-conf.org/proceedings/lrec2008/pdf/536_paper.pdf) (Ienco et al., LREC 2008)
ACL