@inproceedings{yang-etal-2025-towards,
title = "What is it? Towards a Generalizable Native {A}merican Language Identification System",
author = "Yang, Ivory and
Ma, Weicheng and
Alvarez, Carlos Guerrero and
Dinauer, William and
Vosoughi, Soroush",
editor = "Ebrahimi, Abteen and
Haider, Samar and
Liu, Emmy and
Haider, Sammar and
Leonor Pacheco, Maria and
Wein, Shira",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)",
month = apr,
year = "2025",
address = "Albuquerque, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-srw.10/",
doi = "10.18653/v1/2025.naacl-srw.10",
pages = "105--111",
ISBN = "979-8-89176-192-6",
abstract = "This paper presents a research thesis proposal to develop a generalizable Native American language identification system. Despite their cultural and historical significance, Native American languages remain entirely unsupported by major commercial language identification systems. This omission not only underscores the systemic neglect of endangered languages in technological development, but also highlights the urgent need for dedicated, community-driven solutions. We propose a two-pronged approach: (1) systematically curating linguistic resources across all Native American languages for robust training, and (2) tailored data augmentation to generate synthetic yet linguistically coherent training samples. As proof of concept, we extend an existing rudimentary Athabaskan language classifier by integrating Plains Apache, an extinct Southern Athabaskan language, as an additional language class. We also adapt a data generation framework for low-resource languages to create synthetic Plains Apache data, highlighting the potential of data augmentation. This proposal advocates for a community-driven, technological approach to supporting Native American languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2025-towards">
<titleInfo>
<title>What is it? Towards a Generalizable Native American Language Identification System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ivory</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weicheng</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="given">Guerrero</namePart>
<namePart type="family">Alvarez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Dinauer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soroush</namePart>
<namePart type="family">Vosoughi</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 4: Student Research Workshop)</title>
</titleInfo>
<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">Samar</namePart>
<namePart type="family">Haider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmy</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sammar</namePart>
<namePart type="family">Haider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Leonor Pacheco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shira</namePart>
<namePart type="family">Wein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-192-6</identifier>
</relatedItem>
<abstract>This paper presents a research thesis proposal to develop a generalizable Native American language identification system. Despite their cultural and historical significance, Native American languages remain entirely unsupported by major commercial language identification systems. This omission not only underscores the systemic neglect of endangered languages in technological development, but also highlights the urgent need for dedicated, community-driven solutions. We propose a two-pronged approach: (1) systematically curating linguistic resources across all Native American languages for robust training, and (2) tailored data augmentation to generate synthetic yet linguistically coherent training samples. As proof of concept, we extend an existing rudimentary Athabaskan language classifier by integrating Plains Apache, an extinct Southern Athabaskan language, as an additional language class. We also adapt a data generation framework for low-resource languages to create synthetic Plains Apache data, highlighting the potential of data augmentation. This proposal advocates for a community-driven, technological approach to supporting Native American languages.</abstract>
<identifier type="citekey">yang-etal-2025-towards</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-srw.10</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-srw.10/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>105</start>
<end>111</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T What is it? Towards a Generalizable Native American Language Identification System
%A Yang, Ivory
%A Ma, Weicheng
%A Alvarez, Carlos Guerrero
%A Dinauer, William
%A Vosoughi, Soroush
%Y Ebrahimi, Abteen
%Y Haider, Samar
%Y Liu, Emmy
%Y Haider, Sammar
%Y Leonor Pacheco, Maria
%Y Wein, Shira
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, USA
%@ 979-8-89176-192-6
%F yang-etal-2025-towards
%X This paper presents a research thesis proposal to develop a generalizable Native American language identification system. Despite their cultural and historical significance, Native American languages remain entirely unsupported by major commercial language identification systems. This omission not only underscores the systemic neglect of endangered languages in technological development, but also highlights the urgent need for dedicated, community-driven solutions. We propose a two-pronged approach: (1) systematically curating linguistic resources across all Native American languages for robust training, and (2) tailored data augmentation to generate synthetic yet linguistically coherent training samples. As proof of concept, we extend an existing rudimentary Athabaskan language classifier by integrating Plains Apache, an extinct Southern Athabaskan language, as an additional language class. We also adapt a data generation framework for low-resource languages to create synthetic Plains Apache data, highlighting the potential of data augmentation. This proposal advocates for a community-driven, technological approach to supporting Native American languages.
%R 10.18653/v1/2025.naacl-srw.10
%U https://aclanthology.org/2025.naacl-srw.10/
%U https://doi.org/10.18653/v1/2025.naacl-srw.10
%P 105-111
Markdown (Informal)
[What is it? Towards a Generalizable Native American Language Identification System](https://aclanthology.org/2025.naacl-srw.10/) (Yang et al., NAACL 2025)
ACL
- Ivory Yang, Weicheng Ma, Carlos Guerrero Alvarez, William Dinauer, and Soroush Vosoughi. 2025. What is it? Towards a Generalizable Native American Language Identification System. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop), pages 105–111, Albuquerque, USA. Association for Computational Linguistics.