@inproceedings{monachini-etal-2006-unified,
title = "Unified Lexicon and Unified Morphosyntactic Specifications for Written and Spoken {I}talian",
author = "Monachini, Monica and
Calzolari, Nicoletta and
Choukri, Khalid and
Friedrich, Jochen and
Maltese, Giulio and
Mammini, Michele and
Odijk, Jan and
Ulivieri, Marisa",
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/445_pdf.pdf",
abstract = "The goal of this paper is (1) to illustrate a specific procedure for merging different monolingual lexicons, focussing on techniques for detecting and mapping equivalent lexical entries, and (2) to sketch a production model that enables one to obtain lexical resources via unification of existing data. We describe the creation of a Unified Lexicon (UL) from a common sample of the Italian PAROLE-SIMPLE-CLIPS phonological lexicon and of the Italian LCSTAR pronunciation lexicon. We expand previous experiments carried out at ILC-CNR: based on a detailed mechanism for mapping grammatical classifications of candidate UL entries, a consensual set of Unified Morphosyntactic Specifications (UMS) shared by lexica for the written and spoken areas is proposed. The impact of the UL on cross-validation issues is analysed: by looking into conflicts, mismatches and diverging classifications can be detected in both resources. The work presented is in line with the activities promoted by ELRA towards the development of methods for packaging new language resources by combining independently created resources, and was carried out as part of the ELRA Production Committee activities. ELRA aims to exploit the UL experience to carry out such merging activities for resources available on the ELRA catalogue in order to fulfill the users' needs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="monachini-etal-2006-unified">
<titleInfo>
<title>Unified Lexicon and Unified Morphosyntactic Specifications for Written and Spoken Italian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Monica</namePart>
<namePart type="family">Monachini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jochen</namePart>
<namePart type="family">Friedrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giulio</namePart>
<namePart type="family">Maltese</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michele</namePart>
<namePart type="family">Mammini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marisa</namePart>
<namePart type="family">Ulivieri</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>The goal of this paper is (1) to illustrate a specific procedure for merging different monolingual lexicons, focussing on techniques for detecting and mapping equivalent lexical entries, and (2) to sketch a production model that enables one to obtain lexical resources via unification of existing data. We describe the creation of a Unified Lexicon (UL) from a common sample of the Italian PAROLE-SIMPLE-CLIPS phonological lexicon and of the Italian LCSTAR pronunciation lexicon. We expand previous experiments carried out at ILC-CNR: based on a detailed mechanism for mapping grammatical classifications of candidate UL entries, a consensual set of Unified Morphosyntactic Specifications (UMS) shared by lexica for the written and spoken areas is proposed. The impact of the UL on cross-validation issues is analysed: by looking into conflicts, mismatches and diverging classifications can be detected in both resources. The work presented is in line with the activities promoted by ELRA towards the development of methods for packaging new language resources by combining independently created resources, and was carried out as part of the ELRA Production Committee activities. ELRA aims to exploit the UL experience to carry out such merging activities for resources available on the ELRA catalogue in order to fulfill the users’ needs.</abstract>
<identifier type="citekey">monachini-etal-2006-unified</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/445_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unified Lexicon and Unified Morphosyntactic Specifications for Written and Spoken Italian
%A Monachini, Monica
%A Calzolari, Nicoletta
%A Choukri, Khalid
%A Friedrich, Jochen
%A Maltese, Giulio
%A Mammini, Michele
%A Odijk, Jan
%A Ulivieri, Marisa
%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 monachini-etal-2006-unified
%X The goal of this paper is (1) to illustrate a specific procedure for merging different monolingual lexicons, focussing on techniques for detecting and mapping equivalent lexical entries, and (2) to sketch a production model that enables one to obtain lexical resources via unification of existing data. We describe the creation of a Unified Lexicon (UL) from a common sample of the Italian PAROLE-SIMPLE-CLIPS phonological lexicon and of the Italian LCSTAR pronunciation lexicon. We expand previous experiments carried out at ILC-CNR: based on a detailed mechanism for mapping grammatical classifications of candidate UL entries, a consensual set of Unified Morphosyntactic Specifications (UMS) shared by lexica for the written and spoken areas is proposed. The impact of the UL on cross-validation issues is analysed: by looking into conflicts, mismatches and diverging classifications can be detected in both resources. The work presented is in line with the activities promoted by ELRA towards the development of methods for packaging new language resources by combining independently created resources, and was carried out as part of the ELRA Production Committee activities. ELRA aims to exploit the UL experience to carry out such merging activities for resources available on the ELRA catalogue in order to fulfill the users’ needs.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/445_pdf.pdf
Markdown (Informal)
[Unified Lexicon and Unified Morphosyntactic Specifications for Written and Spoken Italian](http://www.lrec-conf.org/proceedings/lrec2006/pdf/445_pdf.pdf) (Monachini et al., LREC 2006)
ACL