@inproceedings{savy-etal-2006-multilevel,
title = "Multilevel corpus analysis: generating and querying an {AG}set of spoken {I}talian ({S}p{I}t-{MD}b).",
author = "Savy, Renata and
Cutugno, Francesco and
Crocco, Claudia",
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/492_pdf.pdf",
abstract = "In this paper we present an application of AGTK to a corpus of spoken Italian annotated at many different linguistic levels. The work consists of two parts: a) the presentation of AG-SpIt, a toolkit devoted to corpus data management that we developed according to AGTK proposals; b) the presentation of corpus structure together with some examples and results of cross-level linguistic analyses obtained querying the database (SpIt-MDb). As this work is still an ongoing investigation, results must be considered preliminary, as a demo illustrating the potentiality of the tool and the advantages it introduces to validate linguistic theories and annotation systems. Currently, SpIt-MDb is a linguistic resource under development; it represents one of the first attempts to create an Italian corpus labelled at various linguistic levels (from acoustic/sub-phonetic, to textual/pragmatic ones) which can be queried in the interrelations among levels.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="savy-etal-2006-multilevel">
<titleInfo>
<title>Multilevel corpus analysis: generating and querying an AGset of spoken Italian (SpIt-MDb).</title>
</titleInfo>
<name type="personal">
<namePart type="given">Renata</namePart>
<namePart type="family">Savy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francesco</namePart>
<namePart type="family">Cutugno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Crocco</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>In this paper we present an application of AGTK to a corpus of spoken Italian annotated at many different linguistic levels. The work consists of two parts: a) the presentation of AG-SpIt, a toolkit devoted to corpus data management that we developed according to AGTK proposals; b) the presentation of corpus structure together with some examples and results of cross-level linguistic analyses obtained querying the database (SpIt-MDb). As this work is still an ongoing investigation, results must be considered preliminary, as a demo illustrating the potentiality of the tool and the advantages it introduces to validate linguistic theories and annotation systems. Currently, SpIt-MDb is a linguistic resource under development; it represents one of the first attempts to create an Italian corpus labelled at various linguistic levels (from acoustic/sub-phonetic, to textual/pragmatic ones) which can be queried in the interrelations among levels.</abstract>
<identifier type="citekey">savy-etal-2006-multilevel</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/492_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multilevel corpus analysis: generating and querying an AGset of spoken Italian (SpIt-MDb).
%A Savy, Renata
%A Cutugno, Francesco
%A Crocco, Claudia
%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 savy-etal-2006-multilevel
%X In this paper we present an application of AGTK to a corpus of spoken Italian annotated at many different linguistic levels. The work consists of two parts: a) the presentation of AG-SpIt, a toolkit devoted to corpus data management that we developed according to AGTK proposals; b) the presentation of corpus structure together with some examples and results of cross-level linguistic analyses obtained querying the database (SpIt-MDb). As this work is still an ongoing investigation, results must be considered preliminary, as a demo illustrating the potentiality of the tool and the advantages it introduces to validate linguistic theories and annotation systems. Currently, SpIt-MDb is a linguistic resource under development; it represents one of the first attempts to create an Italian corpus labelled at various linguistic levels (from acoustic/sub-phonetic, to textual/pragmatic ones) which can be queried in the interrelations among levels.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/492_pdf.pdf
Markdown (Informal)
[Multilevel corpus analysis: generating and querying an AGset of spoken Italian (SpIt-MDb).](http://www.lrec-conf.org/proceedings/lrec2006/pdf/492_pdf.pdf) (Savy et al., LREC 2006)
ACL