@inproceedings{pugh-etal-2025-ihquin,
title = "Ihquin tlahtouah in Tetelahtzincocah: An annotated, multi-purpose audio and text corpus of Western Sierra {P}uebla {N}ahuatl",
author = "Pugh, Robert and
Wing, Cheyenne and
Ju{\'a}rez Huerta, Mar{\'i}a Ximena and
M{\'a}rquez Hernandez, {\'A}ngeles and
Tyers, Francis",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.181/",
doi = "10.18653/v1/2025.naacl-long.181",
pages = "3549--3562",
ISBN = "979-8-89176-189-6",
abstract = "The development of digital linguistic resources is essential for enhancing the inclusion of indigenous and marginalized languages in the digital domain. Indigenous languages of Mexico, despite representing vast typological diversity and millions of speakers, have largely been overlooked in NLP until recently. In this paper, we present a corpus of audio and annotated transcriptions of Western Sierra Puebla Nahuatl, an endangered variety of Nahuatl spoken in Puebla, Mexico. The data made available in this corpus are useful for ASR, spelling normalization, and word-level language identification. We detail the corpus-creation process, and describe experiments to report benchmark results for each of these important NLP tasks. The corpus audio and text is made freely available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pugh-etal-2025-ihquin">
<titleInfo>
<title>Ihquin tlahtouah in Tetelahtzincocah: An annotated, multi-purpose audio and text corpus of Western Sierra Puebla Nahuatl</title>
</titleInfo>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Pugh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cheyenne</namePart>
<namePart type="family">Wing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">María</namePart>
<namePart type="given">Ximena</namePart>
<namePart type="family">Juárez Huerta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ángeles</namePart>
<namePart type="family">Márquez Hernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Tyers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<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">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>The development of digital linguistic resources is essential for enhancing the inclusion of indigenous and marginalized languages in the digital domain. Indigenous languages of Mexico, despite representing vast typological diversity and millions of speakers, have largely been overlooked in NLP until recently. In this paper, we present a corpus of audio and annotated transcriptions of Western Sierra Puebla Nahuatl, an endangered variety of Nahuatl spoken in Puebla, Mexico. The data made available in this corpus are useful for ASR, spelling normalization, and word-level language identification. We detail the corpus-creation process, and describe experiments to report benchmark results for each of these important NLP tasks. The corpus audio and text is made freely available.</abstract>
<identifier type="citekey">pugh-etal-2025-ihquin</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.181</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.181/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>3549</start>
<end>3562</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Ihquin tlahtouah in Tetelahtzincocah: An annotated, multi-purpose audio and text corpus of Western Sierra Puebla Nahuatl
%A Pugh, Robert
%A Wing, Cheyenne
%A Juárez Huerta, María Ximena
%A Márquez Hernandez, Ángeles
%A Tyers, Francis
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F pugh-etal-2025-ihquin
%X The development of digital linguistic resources is essential for enhancing the inclusion of indigenous and marginalized languages in the digital domain. Indigenous languages of Mexico, despite representing vast typological diversity and millions of speakers, have largely been overlooked in NLP until recently. In this paper, we present a corpus of audio and annotated transcriptions of Western Sierra Puebla Nahuatl, an endangered variety of Nahuatl spoken in Puebla, Mexico. The data made available in this corpus are useful for ASR, spelling normalization, and word-level language identification. We detail the corpus-creation process, and describe experiments to report benchmark results for each of these important NLP tasks. The corpus audio and text is made freely available.
%R 10.18653/v1/2025.naacl-long.181
%U https://aclanthology.org/2025.naacl-long.181/
%U https://doi.org/10.18653/v1/2025.naacl-long.181
%P 3549-3562
Markdown (Informal)
[Ihquin tlahtouah in Tetelahtzincocah: An annotated, multi-purpose audio and text corpus of Western Sierra Puebla Nahuatl](https://aclanthology.org/2025.naacl-long.181/) (Pugh et al., NAACL 2025)
ACL