@inproceedings{magnini-etal-2006-cab,
title = "{I}-{CAB}: the {I}talian Content Annotation Bank",
author = "Magnini, B. and
Pianta, E. and
Girardi, C. and
Negri, M. and
Romano, L. and
Speranza, M. and
Bartalesi Lenzi, V. and
Sprugnoli, R.",
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/518_pdf.pdf",
abstract = "In this paper we present work in progress for the creation of the Italian Content Annotation Bank (I-CAB), a corpus of Italian news annotated with semantic information at different levels. The first level is represented by temporal expressions, the second level is represented by different types of entities (i.e. person, organizations, locations and geo-political entities), and the third level is represented by relations between entities (e.g. the affiliation relation connecting a person to an organization). So far I-CAB has been manually annotated with temporal expressions, person entities and organization entities. As we intend I-CAB to become a benchmark for various automatic Information Extraction tasks, we followed a policy of reusing already available markup languages. In particular, we adopted the annotation schemes developed for the ACE Entity Detection and Time Expressions Recognition and Normalization tasks. As the ACE guidelines have originally been developed for English, part of the effort consisted in adapting them to the specific morpho-syntactic features of Italian. Finally, we have extended them to include a wider range of entities, such as conjunctions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="magnini-etal-2006-cab">
<titleInfo>
<title>I-CAB: the Italian Content Annotation Bank</title>
</titleInfo>
<name type="personal">
<namePart type="given">B</namePart>
<namePart type="family">Magnini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">E</namePart>
<namePart type="family">Pianta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">C</namePart>
<namePart type="family">Girardi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">M</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">L</namePart>
<namePart type="family">Romano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">M</namePart>
<namePart type="family">Speranza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">V</namePart>
<namePart type="family">Bartalesi Lenzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">R</namePart>
<namePart type="family">Sprugnoli</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 work in progress for the creation of the Italian Content Annotation Bank (I-CAB), a corpus of Italian news annotated with semantic information at different levels. The first level is represented by temporal expressions, the second level is represented by different types of entities (i.e. person, organizations, locations and geo-political entities), and the third level is represented by relations between entities (e.g. the affiliation relation connecting a person to an organization). So far I-CAB has been manually annotated with temporal expressions, person entities and organization entities. As we intend I-CAB to become a benchmark for various automatic Information Extraction tasks, we followed a policy of reusing already available markup languages. In particular, we adopted the annotation schemes developed for the ACE Entity Detection and Time Expressions Recognition and Normalization tasks. As the ACE guidelines have originally been developed for English, part of the effort consisted in adapting them to the specific morpho-syntactic features of Italian. Finally, we have extended them to include a wider range of entities, such as conjunctions.</abstract>
<identifier type="citekey">magnini-etal-2006-cab</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/518_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T I-CAB: the Italian Content Annotation Bank
%A Magnini, B.
%A Pianta, E.
%A Girardi, C.
%A Negri, M.
%A Romano, L.
%A Speranza, M.
%A Bartalesi Lenzi, V.
%A Sprugnoli, R.
%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 magnini-etal-2006-cab
%X In this paper we present work in progress for the creation of the Italian Content Annotation Bank (I-CAB), a corpus of Italian news annotated with semantic information at different levels. The first level is represented by temporal expressions, the second level is represented by different types of entities (i.e. person, organizations, locations and geo-political entities), and the third level is represented by relations between entities (e.g. the affiliation relation connecting a person to an organization). So far I-CAB has been manually annotated with temporal expressions, person entities and organization entities. As we intend I-CAB to become a benchmark for various automatic Information Extraction tasks, we followed a policy of reusing already available markup languages. In particular, we adopted the annotation schemes developed for the ACE Entity Detection and Time Expressions Recognition and Normalization tasks. As the ACE guidelines have originally been developed for English, part of the effort consisted in adapting them to the specific morpho-syntactic features of Italian. Finally, we have extended them to include a wider range of entities, such as conjunctions.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/518_pdf.pdf
Markdown (Informal)
[I-CAB: the Italian Content Annotation Bank](http://www.lrec-conf.org/proceedings/lrec2006/pdf/518_pdf.pdf) (Magnini et al., LREC 2006)
ACL
- B. Magnini, E. Pianta, C. Girardi, M. Negri, L. Romano, M. Speranza, V. Bartalesi Lenzi, and R. Sprugnoli. 2006. I-CAB: the Italian Content Annotation Bank. In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06), Genoa, Italy. European Language Resources Association (ELRA).