@inproceedings{alexandre-de-alencar-2026-extending,
title = "Extending Enhanced {U}niversal {D}ependencies to Nheengatu: Semi-Automated Control and Raising Annotation",
author = "Alexandre, Dominick Maia and
de Alencar, Leonel Figueiredo",
editor = "Barbosa, Bryan Khelven da Silva and
Paes, Aline and
Felippo, Ariani Di",
booktitle = "Proceedings of the 17th {B}razilian Symposium in Information and Human Language Technology",
month = oct,
year = "2026",
address = "Cuiab{\'a}, Mato Grosso, Brazil",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.stil-1.1/",
doi = "10.5753/stil.2026.26653",
pages = "1--13",
abstract = "This paper presents the first Enhanced Universal Dependencies annotation effort for a Brazilian Indigenous language, focusing on XCOMP constructions in Nheengatu, an endangered Tupian language. We describe a semiautomatic pipeline for the UD Nheengatu-CompLin treebank to annotate control and raising predicates and propagated subjects. The method combines theoretical discussions on XCOMP constructions with corpus-based analysis of Nheengatu syntax to create rule-based enhancement heuristics. The work also provides annotation guidelines and expands EUD resources for Indigenous and low-resource languages within the Universal Dependencies framework."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alexandre-de-alencar-2026-extending">
<titleInfo>
<title>Extending Enhanced Universal Dependencies to Nheengatu: Semi-Automated Control and Raising Annotation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dominick</namePart>
<namePart type="given">Maia</namePart>
<namePart type="family">Alexandre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leonel</namePart>
<namePart type="given">Figueiredo</namePart>
<namePart type="family">de Alencar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Brazilian Symposium in Information and Human Language Technology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bryan</namePart>
<namePart type="given">Khelven</namePart>
<namePart type="given">da</namePart>
<namePart type="given">Silva</namePart>
<namePart type="family">Barbosa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Paes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ariani</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Felippo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Cuiabá, Mato Grosso, Brazil</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents the first Enhanced Universal Dependencies annotation effort for a Brazilian Indigenous language, focusing on XCOMP constructions in Nheengatu, an endangered Tupian language. We describe a semiautomatic pipeline for the UD Nheengatu-CompLin treebank to annotate control and raising predicates and propagated subjects. The method combines theoretical discussions on XCOMP constructions with corpus-based analysis of Nheengatu syntax to create rule-based enhancement heuristics. The work also provides annotation guidelines and expands EUD resources for Indigenous and low-resource languages within the Universal Dependencies framework.</abstract>
<identifier type="citekey">alexandre-de-alencar-2026-extending</identifier>
<identifier type="doi">10.5753/stil.2026.26653</identifier>
<location>
<url>https://aclanthology.org/2026.stil-1.1/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1</start>
<end>13</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extending Enhanced Universal Dependencies to Nheengatu: Semi-Automated Control and Raising Annotation
%A Alexandre, Dominick Maia
%A de Alencar, Leonel Figueiredo
%Y Barbosa, Bryan Khelven da Silva
%Y Paes, Aline
%Y Felippo, Ariani Di
%S Proceedings of the 17th Brazilian Symposium in Information and Human Language Technology
%D 2026
%8 October
%I Association for Computational Linguistics
%C Cuiabá, Mato Grosso, Brazil
%F alexandre-de-alencar-2026-extending
%X This paper presents the first Enhanced Universal Dependencies annotation effort for a Brazilian Indigenous language, focusing on XCOMP constructions in Nheengatu, an endangered Tupian language. We describe a semiautomatic pipeline for the UD Nheengatu-CompLin treebank to annotate control and raising predicates and propagated subjects. The method combines theoretical discussions on XCOMP constructions with corpus-based analysis of Nheengatu syntax to create rule-based enhancement heuristics. The work also provides annotation guidelines and expands EUD resources for Indigenous and low-resource languages within the Universal Dependencies framework.
%R 10.5753/stil.2026.26653
%U https://aclanthology.org/2026.stil-1.1/
%U https://doi.org/10.5753/stil.2026.26653
%P 1-13
Markdown (Informal)
[Extending Enhanced Universal Dependencies to Nheengatu: Semi-Automated Control and Raising Annotation](https://aclanthology.org/2026.stil-1.1/) (Alexandre & de Alencar, STIL 2026)
ACL