@inproceedings{tariq-2026-computational,
title = "Computational Preservation of Endangered Pamiri Languages through {NLP}: Insights from Bartangi and a Roadmap for Digital Inclusion",
author = "Tariq, Warda",
editor = "Atwell, Katherine and
Borah, Angana and
Dementieva, Daryna and
Kreiss, Elisa and
Kotonya, Neema and
Liu, Jiarui and
Olson, Liz and
Wan, Ruyuan and
Zhao, Jieyu",
booktitle = "Proceedings of the Fifth Workshop on {NLP} for Positive Impact ({NLP}4{PI})",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.nlp4pi-1.11/",
pages = "116--124",
ISBN = "979-8-89176-495-8",
abstract = "Endangered languages remain significantly underrepresented in modern Natural Language Processing (NLP) due to the scarcity of foundational computational resources. Although recent advances in multilingual and low-resource NLP have improved language technologies for many underrepresented languages, evaluation commonly emphasizes technical measures such as corpus quality, representation quality, and downstream task performance. While these metrics are essential for assessing computational quality, they provide limited insight into the broader societal impact of NLP resource development, particularly for endangered languages where digital inclusion, cultural preservation, and long-term sustainability are central objectives. In this paper, we propose a conceptual framework for assessing the societal impact of NLP resource development for endangered languages. The framework complements conventional technical evaluation by introducing six dimensions: technical readiness, accessibility, community participation, educational and cultural value, research reusability, and sustainability. We illustrate the application of the framework through the development of computational resources for Bartangi, an endangered Pamiri language, demonstrating how it can be used to identify strengths, limitations, and future priorities beyond technical performance alone. Rather than replacing conventional evaluation, the proposed framework extends it by providing a structured perspective for understanding how foundational NLP resources contribute to responsible AI, digital inclusion, and the long-term computational preservation of endangered languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tariq-2026-computational">
<titleInfo>
<title>Computational Preservation of Endangered Pamiri Languages through NLP: Insights from Bartangi and a Roadmap for Digital Inclusion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Warda</namePart>
<namePart type="family">Tariq</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 Fifth Workshop on NLP for Positive Impact (NLP4PI)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Katherine</namePart>
<namePart type="family">Atwell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angana</namePart>
<namePart type="family">Borah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daryna</namePart>
<namePart type="family">Dementieva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Kreiss</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Neema</namePart>
<namePart type="family">Kotonya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiarui</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liz</namePart>
<namePart type="family">Olson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruyuan</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jieyu</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-495-8</identifier>
</relatedItem>
<abstract>Endangered languages remain significantly underrepresented in modern Natural Language Processing (NLP) due to the scarcity of foundational computational resources. Although recent advances in multilingual and low-resource NLP have improved language technologies for many underrepresented languages, evaluation commonly emphasizes technical measures such as corpus quality, representation quality, and downstream task performance. While these metrics are essential for assessing computational quality, they provide limited insight into the broader societal impact of NLP resource development, particularly for endangered languages where digital inclusion, cultural preservation, and long-term sustainability are central objectives. In this paper, we propose a conceptual framework for assessing the societal impact of NLP resource development for endangered languages. The framework complements conventional technical evaluation by introducing six dimensions: technical readiness, accessibility, community participation, educational and cultural value, research reusability, and sustainability. We illustrate the application of the framework through the development of computational resources for Bartangi, an endangered Pamiri language, demonstrating how it can be used to identify strengths, limitations, and future priorities beyond technical performance alone. Rather than replacing conventional evaluation, the proposed framework extends it by providing a structured perspective for understanding how foundational NLP resources contribute to responsible AI, digital inclusion, and the long-term computational preservation of endangered languages.</abstract>
<identifier type="citekey">tariq-2026-computational</identifier>
<location>
<url>https://aclanthology.org/2026.nlp4pi-1.11/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>116</start>
<end>124</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Computational Preservation of Endangered Pamiri Languages through NLP: Insights from Bartangi and a Roadmap for Digital Inclusion
%A Tariq, Warda
%Y Atwell, Katherine
%Y Borah, Angana
%Y Dementieva, Daryna
%Y Kreiss, Elisa
%Y Kotonya, Neema
%Y Liu, Jiarui
%Y Olson, Liz
%Y Wan, Ruyuan
%Y Zhao, Jieyu
%S Proceedings of the Fifth Workshop on NLP for Positive Impact (NLP4PI)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-495-8
%F tariq-2026-computational
%X Endangered languages remain significantly underrepresented in modern Natural Language Processing (NLP) due to the scarcity of foundational computational resources. Although recent advances in multilingual and low-resource NLP have improved language technologies for many underrepresented languages, evaluation commonly emphasizes technical measures such as corpus quality, representation quality, and downstream task performance. While these metrics are essential for assessing computational quality, they provide limited insight into the broader societal impact of NLP resource development, particularly for endangered languages where digital inclusion, cultural preservation, and long-term sustainability are central objectives. In this paper, we propose a conceptual framework for assessing the societal impact of NLP resource development for endangered languages. The framework complements conventional technical evaluation by introducing six dimensions: technical readiness, accessibility, community participation, educational and cultural value, research reusability, and sustainability. We illustrate the application of the framework through the development of computational resources for Bartangi, an endangered Pamiri language, demonstrating how it can be used to identify strengths, limitations, and future priorities beyond technical performance alone. Rather than replacing conventional evaluation, the proposed framework extends it by providing a structured perspective for understanding how foundational NLP resources contribute to responsible AI, digital inclusion, and the long-term computational preservation of endangered languages.
%U https://aclanthology.org/2026.nlp4pi-1.11/
%P 116-124
Markdown (Informal)
[Computational Preservation of Endangered Pamiri Languages through NLP: Insights from Bartangi and a Roadmap for Digital Inclusion](https://aclanthology.org/2026.nlp4pi-1.11/) (Tariq, NLP4PI 2026)
ACL