@inproceedings{post-palmer-2026-linguistic,
title = "Linguistic Feature Tagging for Automatic Classification of 27 Closely-Related {Q}uechua Varieties",
author = "Post, Claire and
Palmer, Alexis",
editor = "Mager, Manuel and
Ebrahimi, Abteen and
Bui, Minh Duc and
Pugh, Robert and
Oncevay, Arturo and
Chiruzzo, Luis and
Solano, Rolando Coto and
Rijhwani, Shruti and
Von Der Wense, Katharina",
booktitle = "Proceedings of the Sixth Workshop on {NLP} for Indigenous Languages of the {A}mericas ({A}mericas{NLP})",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.americasnlp-6.5/",
pages = "46--63",
ISBN = "979-8-89176-415-6",
abstract = "This paper presents a multi-dialect text classifier for Quechua that augments neural models with rule-based linguistic information to address challenges in low-resource, morphologically complex settings. The approach is built on a carefully curated dataset spanning multiple genres, including annotated parallel bible corpora, and encodes manually annotated lexical variation and polypersonal verbal agreement as explicit features within a transformer-based classifier. Results show that neural models substantially outperform statistical baselines, enabling highly accurate multi-class classification across 27 Quechua dialects. The impact of linguistic augmentation is context-dependent: gains are minimal in high-resource settings but more pronounced in low-resource and cross-domain conditions. Overall, this work aims to contribute to the development of dialect-sensitive NLP methods for Quechua and other low-resource, morphologically rich languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="post-palmer-2026-linguistic">
<titleInfo>
<title>Linguistic Feature Tagging for Automatic Classification of 27 Closely-Related Quechua Varieties</title>
</titleInfo>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="family">Post</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manuel</namePart>
<namePart type="family">Mager</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abteen</namePart>
<namePart type="family">Ebrahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minh</namePart>
<namePart type="given">Duc</namePart>
<namePart type="family">Bui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Pugh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arturo</namePart>
<namePart type="family">Oncevay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rolando</namePart>
<namePart type="given">Coto</namePart>
<namePart type="family">Solano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shruti</namePart>
<namePart type="family">Rijhwani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">Von Der Wense</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-415-6</identifier>
</relatedItem>
<abstract>This paper presents a multi-dialect text classifier for Quechua that augments neural models with rule-based linguistic information to address challenges in low-resource, morphologically complex settings. The approach is built on a carefully curated dataset spanning multiple genres, including annotated parallel bible corpora, and encodes manually annotated lexical variation and polypersonal verbal agreement as explicit features within a transformer-based classifier. Results show that neural models substantially outperform statistical baselines, enabling highly accurate multi-class classification across 27 Quechua dialects. The impact of linguistic augmentation is context-dependent: gains are minimal in high-resource settings but more pronounced in low-resource and cross-domain conditions. Overall, this work aims to contribute to the development of dialect-sensitive NLP methods for Quechua and other low-resource, morphologically rich languages.</abstract>
<identifier type="citekey">post-palmer-2026-linguistic</identifier>
<location>
<url>https://aclanthology.org/2026.americasnlp-6.5/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>46</start>
<end>63</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Linguistic Feature Tagging for Automatic Classification of 27 Closely-Related Quechua Varieties
%A Post, Claire
%A Palmer, Alexis
%Y Mager, Manuel
%Y Ebrahimi, Abteen
%Y Bui, Minh Duc
%Y Pugh, Robert
%Y Oncevay, Arturo
%Y Chiruzzo, Luis
%Y Solano, Rolando Coto
%Y Rijhwani, Shruti
%Y Von Der Wense, Katharina
%S Proceedings of the Sixth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-415-6
%F post-palmer-2026-linguistic
%X This paper presents a multi-dialect text classifier for Quechua that augments neural models with rule-based linguistic information to address challenges in low-resource, morphologically complex settings. The approach is built on a carefully curated dataset spanning multiple genres, including annotated parallel bible corpora, and encodes manually annotated lexical variation and polypersonal verbal agreement as explicit features within a transformer-based classifier. Results show that neural models substantially outperform statistical baselines, enabling highly accurate multi-class classification across 27 Quechua dialects. The impact of linguistic augmentation is context-dependent: gains are minimal in high-resource settings but more pronounced in low-resource and cross-domain conditions. Overall, this work aims to contribute to the development of dialect-sensitive NLP methods for Quechua and other low-resource, morphologically rich languages.
%U https://aclanthology.org/2026.americasnlp-6.5/
%P 46-63
Markdown (Informal)
[Linguistic Feature Tagging for Automatic Classification of 27 Closely-Related Quechua Varieties](https://aclanthology.org/2026.americasnlp-6.5/) (Post & Palmer, AmericasNLP 2026)
ACL