@inproceedings{zevallos-etal-2026-amazonianlp,
title = "{A}mazonia{NLP}: A Survey of Extreme Low-Resource Languages in the {P}eruvian-{B}razilian {A}mazon",
author = "Zevallos, Rodolfo Joel and
Carraro, Fabr{\'i}cio and
Ortega, John E.",
editor = "Ojha, Atul Kr. and
Sakti, Sakriani and
Soria, Claudia and
Melero, Maite and
McCrae, John P. and
Lignos, Constantine and
Liu, Chao-Hong and
Claramunt, German Rigau and
Rehm, Georg",
booktitle = "Proceedings of the {SIGUL} 2026 Joint Workshop with {ELE}, {EURALI}, and {DCLRL}: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages",
month = may,
year = "2026",
address = "Palma, Mallorca, Spain",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.sigul-1.28/",
doi = "10.63317/3sbz29bn779p",
pages = "280--287",
abstract = "The Amazon basin along the Peru{--}Brazil border hosts extraordinary linguistic diversity, including many Indigenous languages whose speaker communities span national frontiers. Despite sustained documentation work, most remain extremely low-resource languages (ELRLs) for Natural Language Processing (NLP): reusable corpora are scarce, orthographies vary across countries and institutions, and basic tools such as tokenizers, taggers, and morphological analyzers are largely unavailable. We present a resource-oriented survey of five Indigenous languages of the Western Amazon{---}Mats{\'e}s, Amahuaca, Kashinawa, Ticuna, and Kukama-Kukamiria{---}aimed at supporting more realistic NLP and speech work in extreme low-resource settings. Using a systematic search across academic venues, language archives, and public code/model repositories, we identify and cross-check available materials spanning lexical resources, text corpora, linguistic annotation, and speech collections. For each item we record practical reuse information, including the relevant task or modality, source location, and any stated access, licensing, or usage conditions. Our findings show strong cross-language asymmetries and fragmentation: most materials concentrate in documentation artifacts and lexicons, while standardized datasets with clear access and reuse conditions suitable for training and evaluation remain rare. We conclude with concrete recommendations to improve discoverability, normalize orthographic variation, and prioritize resource creation that maximizes interoperability across tools and benchmarks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zevallos-etal-2026-amazonianlp">
<titleInfo>
<title>AmazoniaNLP: A Survey of Extreme Low-Resource Languages in the Peruvian-Brazilian Amazon</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rodolfo</namePart>
<namePart type="given">Joel</namePart>
<namePart type="family">Zevallos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabrício</namePart>
<namePart type="family">Carraro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Ortega</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</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>
<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">John</namePart>
<namePart type="given">P</namePart>
<namePart type="family">McCrae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantine</namePart>
<namePart type="family">Lignos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-Hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="given">Rigau</namePart>
<namePart type="family">Claramunt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Amazon basin along the Peru–Brazil border hosts extraordinary linguistic diversity, including many Indigenous languages whose speaker communities span national frontiers. Despite sustained documentation work, most remain extremely low-resource languages (ELRLs) for Natural Language Processing (NLP): reusable corpora are scarce, orthographies vary across countries and institutions, and basic tools such as tokenizers, taggers, and morphological analyzers are largely unavailable. We present a resource-oriented survey of five Indigenous languages of the Western Amazon—Matsés, Amahuaca, Kashinawa, Ticuna, and Kukama-Kukamiria—aimed at supporting more realistic NLP and speech work in extreme low-resource settings. Using a systematic search across academic venues, language archives, and public code/model repositories, we identify and cross-check available materials spanning lexical resources, text corpora, linguistic annotation, and speech collections. For each item we record practical reuse information, including the relevant task or modality, source location, and any stated access, licensing, or usage conditions. Our findings show strong cross-language asymmetries and fragmentation: most materials concentrate in documentation artifacts and lexicons, while standardized datasets with clear access and reuse conditions suitable for training and evaluation remain rare. We conclude with concrete recommendations to improve discoverability, normalize orthographic variation, and prioritize resource creation that maximizes interoperability across tools and benchmarks.</abstract>
<identifier type="citekey">zevallos-etal-2026-amazonianlp</identifier>
<identifier type="doi">10.63317/3sbz29bn779p</identifier>
<location>
<url>https://aclanthology.org/2026.sigul-1.28/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>280</start>
<end>287</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AmazoniaNLP: A Survey of Extreme Low-Resource Languages in the Peruvian-Brazilian Amazon
%A Zevallos, Rodolfo Joel
%A Carraro, Fabrício
%A Ortega, John E.
%Y Ojha, Atul Kr.
%Y Sakti, Sakriani
%Y Soria, Claudia
%Y Melero, Maite
%Y McCrae, John P.
%Y Lignos, Constantine
%Y Liu, Chao-Hong
%Y Claramunt, German Rigau
%Y Rehm, Georg
%S Proceedings of the SIGUL 2026 Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered Languages
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca, Spain
%F zevallos-etal-2026-amazonianlp
%X The Amazon basin along the Peru–Brazil border hosts extraordinary linguistic diversity, including many Indigenous languages whose speaker communities span national frontiers. Despite sustained documentation work, most remain extremely low-resource languages (ELRLs) for Natural Language Processing (NLP): reusable corpora are scarce, orthographies vary across countries and institutions, and basic tools such as tokenizers, taggers, and morphological analyzers are largely unavailable. We present a resource-oriented survey of five Indigenous languages of the Western Amazon—Matsés, Amahuaca, Kashinawa, Ticuna, and Kukama-Kukamiria—aimed at supporting more realistic NLP and speech work in extreme low-resource settings. Using a systematic search across academic venues, language archives, and public code/model repositories, we identify and cross-check available materials spanning lexical resources, text corpora, linguistic annotation, and speech collections. For each item we record practical reuse information, including the relevant task or modality, source location, and any stated access, licensing, or usage conditions. Our findings show strong cross-language asymmetries and fragmentation: most materials concentrate in documentation artifacts and lexicons, while standardized datasets with clear access and reuse conditions suitable for training and evaluation remain rare. We conclude with concrete recommendations to improve discoverability, normalize orthographic variation, and prioritize resource creation that maximizes interoperability across tools and benchmarks.
%R 10.63317/3sbz29bn779p
%U https://aclanthology.org/2026.sigul-1.28/
%U https://doi.org/10.63317/3sbz29bn779p
%P 280-287
Markdown (Informal)
[AmazoniaNLP: A Survey of Extreme Low-Resource Languages in the Peruvian-Brazilian Amazon](https://aclanthology.org/2026.sigul-1.28/) (Zevallos et al., SIGUL-EURALI-DCLRL 2026)
ACL