@inproceedings{branco-etal-2022-universal,
title = "Universal Grammatical Dependencies for {P}ortuguese with {CINTIL} Data, {LX} Processing and {CLARIN} support",
author = "Branco, Ant{\'o}nio and
Silva, Jo{\~a}o Ricardo and
Gomes, Lu{\'\i}s and
Ant{\'o}nio Rodrigues, Jo{\~a}o",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.603",
pages = "5617--5626",
abstract = "The grammatical framework for the mapping between linguistic form and meaning representation known as Universal Dependencies relies on a non-constituency syntactic analysis that is centered on the notion of grammatical relation (e.g. Subject, Object, etc.). Given its core goal of providing a common set of analysis primitives suitable to every natural language, and its practical objective of fostering their computational grammatical processing, it keeps being an active domain of research in science and technology of language. This paper presents a new collection of quality language resources for the computational processing of the Portuguese language under the Universal Dependencies framework (UD). This is an all-encompassing, publicly available open collection of mutually consistent and inter-operable scientific resources that includes reliably annotated corpora, top-performing processing tools and expert support services: a new UPOS-annotated corpus, CINTIL-UPos, with 675K tokens and a new UD treebank, CINTIL-UDep Treebank, with nearly 38K sentences; a UPOS tagger, LX-UTagger, and a UD parser, LX-UDParser, trained on these corpora, available both as local stand-alone tools and as remote web-based services; and helpdesk support ensured by the Knowledge Center for the Science and Technology of Portuguese of the CLARIN research infrastructure.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="branco-etal-2022-universal">
<titleInfo>
<title>Universal Grammatical Dependencies for Portuguese with CINTIL Data, LX Processing and CLARIN support</title>
</titleInfo>
<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">João</namePart>
<namePart type="given">Ricardo</namePart>
<namePart type="family">Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luís</namePart>
<namePart type="family">Gomes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">António Rodrigues</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The grammatical framework for the mapping between linguistic form and meaning representation known as Universal Dependencies relies on a non-constituency syntactic analysis that is centered on the notion of grammatical relation (e.g. Subject, Object, etc.). Given its core goal of providing a common set of analysis primitives suitable to every natural language, and its practical objective of fostering their computational grammatical processing, it keeps being an active domain of research in science and technology of language. This paper presents a new collection of quality language resources for the computational processing of the Portuguese language under the Universal Dependencies framework (UD). This is an all-encompassing, publicly available open collection of mutually consistent and inter-operable scientific resources that includes reliably annotated corpora, top-performing processing tools and expert support services: a new UPOS-annotated corpus, CINTIL-UPos, with 675K tokens and a new UD treebank, CINTIL-UDep Treebank, with nearly 38K sentences; a UPOS tagger, LX-UTagger, and a UD parser, LX-UDParser, trained on these corpora, available both as local stand-alone tools and as remote web-based services; and helpdesk support ensured by the Knowledge Center for the Science and Technology of Portuguese of the CLARIN research infrastructure.</abstract>
<identifier type="citekey">branco-etal-2022-universal</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.603</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>5617</start>
<end>5626</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Universal Grammatical Dependencies for Portuguese with CINTIL Data, LX Processing and CLARIN support
%A Branco, António
%A Silva, João Ricardo
%A Gomes, Luís
%A António Rodrigues, João
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F branco-etal-2022-universal
%X The grammatical framework for the mapping between linguistic form and meaning representation known as Universal Dependencies relies on a non-constituency syntactic analysis that is centered on the notion of grammatical relation (e.g. Subject, Object, etc.). Given its core goal of providing a common set of analysis primitives suitable to every natural language, and its practical objective of fostering their computational grammatical processing, it keeps being an active domain of research in science and technology of language. This paper presents a new collection of quality language resources for the computational processing of the Portuguese language under the Universal Dependencies framework (UD). This is an all-encompassing, publicly available open collection of mutually consistent and inter-operable scientific resources that includes reliably annotated corpora, top-performing processing tools and expert support services: a new UPOS-annotated corpus, CINTIL-UPos, with 675K tokens and a new UD treebank, CINTIL-UDep Treebank, with nearly 38K sentences; a UPOS tagger, LX-UTagger, and a UD parser, LX-UDParser, trained on these corpora, available both as local stand-alone tools and as remote web-based services; and helpdesk support ensured by the Knowledge Center for the Science and Technology of Portuguese of the CLARIN research infrastructure.
%U https://aclanthology.org/2022.lrec-1.603
%P 5617-5626
Markdown (Informal)
[Universal Grammatical Dependencies for Portuguese with CINTIL Data, LX Processing and CLARIN support](https://aclanthology.org/2022.lrec-1.603) (Branco et al., LREC 2022)
ACL