@inproceedings{lenci-etal-2010-building,
title = "Building an {I}talian {F}rame{N}et through Semi-automatic Corpus Analysis",
author = "Lenci, Alessandro and
Johnson, Martina and
Lapesa, Gabriella",
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/313_Paper.pdf",
abstract = "n this paper, we outline the methodology we adopted to develop a FrameNet for Italian. The main element of novelty with respect to the original FrameNet is represented by the fact that the creation and annotation of Lexical Units is strictly grounded in distributional information (statistical distribution of verbal subcategorization frames, lexical and semantic preferences of each frame) automatically acquired from a large, dependency-parsed corpus. We claim that this approach allows us to overcome some of the shortcomings of the classical lexicographic method used to create FrameNet, by complementing the accuracy of manual annotation with the robustness of data on the global distributional patterns of a verb. In the paper, we describe our method for extracting distributional data from the corpus and the way we used it for the encoding and annotation of LUs. The long-term goal of our project is to create an electronic lexicon for Italian similar to the original English FrameNet. For the moment, we have developed a database of syntactic valences that will be made freely accessible via a web interface. This represents an autonomous resource besides the FrameNet lexicon, of which we have a beginning nucleus consisting of 791 annotated sentences.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lenci-etal-2010-building">
<titleInfo>
<title>Building an Italian FrameNet through Semi-automatic Corpus Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martina</namePart>
<namePart type="family">Johnson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriella</namePart>
<namePart type="family">Lapesa</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>n this paper, we outline the methodology we adopted to develop a FrameNet for Italian. The main element of novelty with respect to the original FrameNet is represented by the fact that the creation and annotation of Lexical Units is strictly grounded in distributional information (statistical distribution of verbal subcategorization frames, lexical and semantic preferences of each frame) automatically acquired from a large, dependency-parsed corpus. We claim that this approach allows us to overcome some of the shortcomings of the classical lexicographic method used to create FrameNet, by complementing the accuracy of manual annotation with the robustness of data on the global distributional patterns of a verb. In the paper, we describe our method for extracting distributional data from the corpus and the way we used it for the encoding and annotation of LUs. The long-term goal of our project is to create an electronic lexicon for Italian similar to the original English FrameNet. For the moment, we have developed a database of syntactic valences that will be made freely accessible via a web interface. This represents an autonomous resource besides the FrameNet lexicon, of which we have a beginning nucleus consisting of 791 annotated sentences.</abstract>
<identifier type="citekey">lenci-etal-2010-building</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/313_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building an Italian FrameNet through Semi-automatic Corpus Analysis
%A Lenci, Alessandro
%A Johnson, Martina
%A Lapesa, Gabriella
%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 lenci-etal-2010-building
%X n this paper, we outline the methodology we adopted to develop a FrameNet for Italian. The main element of novelty with respect to the original FrameNet is represented by the fact that the creation and annotation of Lexical Units is strictly grounded in distributional information (statistical distribution of verbal subcategorization frames, lexical and semantic preferences of each frame) automatically acquired from a large, dependency-parsed corpus. We claim that this approach allows us to overcome some of the shortcomings of the classical lexicographic method used to create FrameNet, by complementing the accuracy of manual annotation with the robustness of data on the global distributional patterns of a verb. In the paper, we describe our method for extracting distributional data from the corpus and the way we used it for the encoding and annotation of LUs. The long-term goal of our project is to create an electronic lexicon for Italian similar to the original English FrameNet. For the moment, we have developed a database of syntactic valences that will be made freely accessible via a web interface. This represents an autonomous resource besides the FrameNet lexicon, of which we have a beginning nucleus consisting of 791 annotated sentences.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/313_Paper.pdf
Markdown (Informal)
[Building an Italian FrameNet through Semi-automatic Corpus Analysis](http://www.lrec-conf.org/proceedings/lrec2010/pdf/313_Paper.pdf) (Lenci et al., LREC 2010)
ACL