@inproceedings{martin-rodriguez-etal-2022-tupian,
title = "Tup{\'i}an Language Ressources: Data, Tools, Analyses",
author = "Mart{\'i}n Rodr{\'i}guez, Lorena and
Merzhevich, Tatiana and
Silva, Wellington and
Tresoldi, Tiago and
Aragon, Carolina and
Gerardi, Fabr{\'i}cio F.",
editor = "Melero, Maite and
Sakti, Sakriani and
Soria, Claudia",
booktitle = "Proceedings of the 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.sigul-1.7/",
pages = "48--58",
abstract = "TuLaR (Tupian Language Resources) is a project for collecting, documenting, analyzing, and developing computational and pedagogical material for low-resource Brazilian indigenous languages. It provides valuable data for language research regarding typological, syntactic, morphological, and phonological aspects. Here we present TuLaR`s databases, with special consideration to TuDeT (Tupian Dependency Treebanks), an annotated corpus under development for nine languages of the Tupian family, built upon the Universal Dependencies framework. The annotation within such a framework serves a twofold goal: enriching the linguistic documentation of the Tupian languages due to the rapid and consistent annotation, and providing computational resources for those languages, thanks to the suitability of our framework for developing NLP tools. We likewise present a related lexical database, some tools developed by the project, and examine future goals for our initiative."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="martin-rodriguez-etal-2022-tupian">
<titleInfo>
<title>Tupían Language Ressources: Data, Tools, Analyses</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lorena</namePart>
<namePart type="family">Martín Rodríguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tatiana</namePart>
<namePart type="family">Merzhevich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wellington</namePart>
<namePart type="family">Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tiago</namePart>
<namePart type="family">Tresoldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolina</namePart>
<namePart type="family">Aragon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabrício</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Gerardi</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 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Melero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Soria</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>TuLaR (Tupian Language Resources) is a project for collecting, documenting, analyzing, and developing computational and pedagogical material for low-resource Brazilian indigenous languages. It provides valuable data for language research regarding typological, syntactic, morphological, and phonological aspects. Here we present TuLaR‘s databases, with special consideration to TuDeT (Tupian Dependency Treebanks), an annotated corpus under development for nine languages of the Tupian family, built upon the Universal Dependencies framework. The annotation within such a framework serves a twofold goal: enriching the linguistic documentation of the Tupian languages due to the rapid and consistent annotation, and providing computational resources for those languages, thanks to the suitability of our framework for developing NLP tools. We likewise present a related lexical database, some tools developed by the project, and examine future goals for our initiative.</abstract>
<identifier type="citekey">martin-rodriguez-etal-2022-tupian</identifier>
<location>
<url>https://aclanthology.org/2022.sigul-1.7/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>48</start>
<end>58</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tupían Language Ressources: Data, Tools, Analyses
%A Martín Rodríguez, Lorena
%A Merzhevich, Tatiana
%A Silva, Wellington
%A Tresoldi, Tiago
%A Aragon, Carolina
%A Gerardi, Fabrício F.
%Y Melero, Maite
%Y Sakti, Sakriani
%Y Soria, Claudia
%S Proceedings of the 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F martin-rodriguez-etal-2022-tupian
%X TuLaR (Tupian Language Resources) is a project for collecting, documenting, analyzing, and developing computational and pedagogical material for low-resource Brazilian indigenous languages. It provides valuable data for language research regarding typological, syntactic, morphological, and phonological aspects. Here we present TuLaR‘s databases, with special consideration to TuDeT (Tupian Dependency Treebanks), an annotated corpus under development for nine languages of the Tupian family, built upon the Universal Dependencies framework. The annotation within such a framework serves a twofold goal: enriching the linguistic documentation of the Tupian languages due to the rapid and consistent annotation, and providing computational resources for those languages, thanks to the suitability of our framework for developing NLP tools. We likewise present a related lexical database, some tools developed by the project, and examine future goals for our initiative.
%U https://aclanthology.org/2022.sigul-1.7/
%P 48-58
Markdown (Informal)
[Tupían Language Ressources: Data, Tools, Analyses](https://aclanthology.org/2022.sigul-1.7/) (Martín Rodríguez et al., SIGUL 2022)
ACL
- Lorena Martín Rodríguez, Tatiana Merzhevich, Wellington Silva, Tiago Tresoldi, Carolina Aragon, and Fabrício F. Gerardi. 2022. Tupían Language Ressources: Data, Tools, Analyses. In Proceedings of the 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages, pages 48–58, Marseille, France. European Language Resources Association.