@inproceedings{barreto-etal-2006-open,
title = "Open Resources and Tools for the Shallow Processing of {P}ortuguese: The {T}ag{S}hare Project",
author = "Barreto, Florbela and
Branco, Ant{\'o}nio and
Ferreira, Eduardo and
Mendes, Am{\'a}lia and
Nascimento, Maria Fernanda Bacelar do and
Nunes, Filipe and
Silva, Jo{\~a}o Ricardo",
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/311_pdf.pdf",
abstract = "This paper presents the TagShare project and the linguistic resources and tools for the shallow processing of Portuguese developed in its scope. These resources include a 1 million token corpus that has been accurately hand annotated with a variety of linguistic information, as well as several state of the art shallow processing tools capable of automatically producing that type of annotation. At present, the linguistic annotations in the corpus are sentence and paragraph boundaries, token boundaries, morphosyntactic POS categories, values of inflection features, lemmas and namedentities. Hence, the set of tools comprise a sentence chunker, a tokenizer, a POS tagger, nominal and verbal analyzers and lemmatizers, a verbal conjugator, a nominal inflector, and a namedentity recognizer, some of which underline several online services.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="barreto-etal-2006-open">
<titleInfo>
<title>Open Resources and Tools for the Shallow Processing of Portuguese: The TagShare Project</title>
</titleInfo>
<name type="personal">
<namePart type="given">Florbela</namePart>
<namePart type="family">Barreto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">António</namePart>
<namePart type="family">Branco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eduardo</namePart>
<namePart type="family">Ferreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amália</namePart>
<namePart type="family">Mendes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Fernanda</namePart>
<namePart type="given">Bacelar</namePart>
<namePart type="given">do</namePart>
<namePart type="family">Nascimento</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Filipe</namePart>
<namePart type="family">Nunes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="given">Ricardo</namePart>
<namePart type="family">Silva</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>This paper presents the TagShare project and the linguistic resources and tools for the shallow processing of Portuguese developed in its scope. These resources include a 1 million token corpus that has been accurately hand annotated with a variety of linguistic information, as well as several state of the art shallow processing tools capable of automatically producing that type of annotation. At present, the linguistic annotations in the corpus are sentence and paragraph boundaries, token boundaries, morphosyntactic POS categories, values of inflection features, lemmas and namedentities. Hence, the set of tools comprise a sentence chunker, a tokenizer, a POS tagger, nominal and verbal analyzers and lemmatizers, a verbal conjugator, a nominal inflector, and a namedentity recognizer, some of which underline several online services.</abstract>
<identifier type="citekey">barreto-etal-2006-open</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/311_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Open Resources and Tools for the Shallow Processing of Portuguese: The TagShare Project
%A Barreto, Florbela
%A Branco, António
%A Ferreira, Eduardo
%A Mendes, Amália
%A Nascimento, Maria Fernanda Bacelar do
%A Nunes, Filipe
%A Silva, João Ricardo
%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 barreto-etal-2006-open
%X This paper presents the TagShare project and the linguistic resources and tools for the shallow processing of Portuguese developed in its scope. These resources include a 1 million token corpus that has been accurately hand annotated with a variety of linguistic information, as well as several state of the art shallow processing tools capable of automatically producing that type of annotation. At present, the linguistic annotations in the corpus are sentence and paragraph boundaries, token boundaries, morphosyntactic POS categories, values of inflection features, lemmas and namedentities. Hence, the set of tools comprise a sentence chunker, a tokenizer, a POS tagger, nominal and verbal analyzers and lemmatizers, a verbal conjugator, a nominal inflector, and a namedentity recognizer, some of which underline several online services.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/311_pdf.pdf
Markdown (Informal)
[Open Resources and Tools for the Shallow Processing of Portuguese: The TagShare Project](http://www.lrec-conf.org/proceedings/lrec2006/pdf/311_pdf.pdf) (Barreto et al., LREC 2006)
ACL