@inproceedings{pereira-etal-2026-unsupervised,
title = "Unsupervised Subword Segmentation for {POS} Tagging in Low-Resource Agglutinative Languages",
author = "Pereira, Jonas Oliveira and
de Sousa, Lilian Teixeira and
Souza, Marlo",
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-1.54/",
doi = "10.5753/stil.2026.29489",
pages = "588--593",
abstract = "While Part-of-speech tagging is considered a well-understood task in the literature, most work has focused on indo-european languages with fusional morphology. For low-resource agglutinative languages, such as brazillian indigenous languages, the task is commonly constrained by small annotated corpora, high lexical sparsity, and morphological patterns that are poorly represented by word-level models. This paper investigates the impact of unsupervised subword segmentation techniques on POS tagging for brazillian indigenous languages. We compare a word-level baseline with Byte Pair Encoding, Morfessor, and FlatCat on Bororo, Nheengatu, and Tupinamba corpora, including a controlled experiment on the size of the training corpus. Our findings suggest that unsupervised segmentation can reduce sparsity in low-resource POS tagging, although its benefit depends on the language, corpus size, and segmentation method."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pereira-etal-2026-unsupervised">
<titleInfo>
<title>Unsupervised Subword Segmentation for POS Tagging in Low-Resource Agglutinative Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonas</namePart>
<namePart type="given">Oliveira</namePart>
<namePart type="family">Pereira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lilian</namePart>
<namePart type="given">Teixeira</namePart>
<namePart type="family">de Sousa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marlo</namePart>
<namePart type="family">Souza</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>While Part-of-speech tagging is considered a well-understood task in the literature, most work has focused on indo-european languages with fusional morphology. For low-resource agglutinative languages, such as brazillian indigenous languages, the task is commonly constrained by small annotated corpora, high lexical sparsity, and morphological patterns that are poorly represented by word-level models. This paper investigates the impact of unsupervised subword segmentation techniques on POS tagging for brazillian indigenous languages. We compare a word-level baseline with Byte Pair Encoding, Morfessor, and FlatCat on Bororo, Nheengatu, and Tupinamba corpora, including a controlled experiment on the size of the training corpus. Our findings suggest that unsupervised segmentation can reduce sparsity in low-resource POS tagging, although its benefit depends on the language, corpus size, and segmentation method.</abstract>
<identifier type="citekey">pereira-etal-2026-unsupervised</identifier>
<identifier type="doi">10.5753/stil.2026.29489</identifier>
<location>
<url>https://aclanthology.org/2026.stil-1.54/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>588</start>
<end>593</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Subword Segmentation for POS Tagging in Low-Resource Agglutinative Languages
%A Pereira, Jonas Oliveira
%A de Sousa, Lilian Teixeira
%A Souza, Marlo
%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 pereira-etal-2026-unsupervised
%X While Part-of-speech tagging is considered a well-understood task in the literature, most work has focused on indo-european languages with fusional morphology. For low-resource agglutinative languages, such as brazillian indigenous languages, the task is commonly constrained by small annotated corpora, high lexical sparsity, and morphological patterns that are poorly represented by word-level models. This paper investigates the impact of unsupervised subword segmentation techniques on POS tagging for brazillian indigenous languages. We compare a word-level baseline with Byte Pair Encoding, Morfessor, and FlatCat on Bororo, Nheengatu, and Tupinamba corpora, including a controlled experiment on the size of the training corpus. Our findings suggest that unsupervised segmentation can reduce sparsity in low-resource POS tagging, although its benefit depends on the language, corpus size, and segmentation method.
%R 10.5753/stil.2026.29489
%U https://aclanthology.org/2026.stil-1.54/
%U https://doi.org/10.5753/stil.2026.29489
%P 588-593
Markdown (Informal)
[Unsupervised Subword Segmentation for POS Tagging in Low-Resource Agglutinative Languages](https://aclanthology.org/2026.stil-1.54/) (Pereira et al., STIL 2026)
ACL