@inproceedings{traore-etal-2026-reclaiming,
title = "Reclaiming {A}frican Voices: Surveying Indigenous Writing Systems for Inclusive {NLP}",
author = "Traore, Mamady and
Le, Ngoc Tan and
Sadat, Fatiha",
editor = "Matfunjwa, Muzi and
Setaka, Mmasibidi and
Mabuya, Rooweither and
van Zaanen, Menno",
booktitle = "Proceedings of Resources for {A}frican Indigenous Languages ({RAIL}) 2026 @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.rail-1.10/",
doi = "10.63317/2zgo4ih7o2ch",
pages = "96--106",
abstract = "Multilingual NLP has expanded rapidly through large-scale pretraining and cross-lingual transfer, yet this progress remains structurally uneven across writing systems. This survey reframes multilingual NLP around scripts rather than languages, arguing that writing systems constitute an under-theorized axis of computational inequality. Focusing on African scripts {---} Indigenous (Vai, Ge{'}ez, Tifinagh), modern (ADLaM, N{'}Ko), and adapted Arabic-based (Ajami){---}we analyze how script properties interact with digital infrastructure, tokenization, and downstream task performance. We organize the literature across four analytical layers: infrastructural (Unicode and input systems), representational (segmentation efficiency and vocabulary allocation), functional (task-level disparities), and epistemic (evaluation bias and the ``low-resource'' framing). Synthesizing evidence from 47 studies, we show that performance gaps across scripts arise primarily from engineering design choices rather than intrinsic linguistic complexity. We conclude by outlining a research agenda for native multiscript foundation models, including script-aware scaling laws, tokenizer equity metrics, and evaluation reform. We argue that multiscript equity is not a peripheral concern but a structural precondition for genuine multilingual inclusion"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="traore-etal-2026-reclaiming">
<titleInfo>
<title>Reclaiming African Voices: Surveying Indigenous Writing Systems for Inclusive NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mamady</namePart>
<namePart type="family">Traore</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ngoc</namePart>
<namePart type="given">Tan</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fatiha</namePart>
<namePart type="family">Sadat</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 Resources for African Indigenous Languages (RAIL) 2026 @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muzi</namePart>
<namePart type="family">Matfunjwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mmasibidi</namePart>
<namePart type="family">Setaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rooweither</namePart>
<namePart type="family">Mabuya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Menno</namePart>
<namePart type="family">van Zaanen</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>Multilingual NLP has expanded rapidly through large-scale pretraining and cross-lingual transfer, yet this progress remains structurally uneven across writing systems. This survey reframes multilingual NLP around scripts rather than languages, arguing that writing systems constitute an under-theorized axis of computational inequality. Focusing on African scripts — Indigenous (Vai, Ge’ez, Tifinagh), modern (ADLaM, N’Ko), and adapted Arabic-based (Ajami)—we analyze how script properties interact with digital infrastructure, tokenization, and downstream task performance. We organize the literature across four analytical layers: infrastructural (Unicode and input systems), representational (segmentation efficiency and vocabulary allocation), functional (task-level disparities), and epistemic (evaluation bias and the “low-resource” framing). Synthesizing evidence from 47 studies, we show that performance gaps across scripts arise primarily from engineering design choices rather than intrinsic linguistic complexity. We conclude by outlining a research agenda for native multiscript foundation models, including script-aware scaling laws, tokenizer equity metrics, and evaluation reform. We argue that multiscript equity is not a peripheral concern but a structural precondition for genuine multilingual inclusion</abstract>
<identifier type="citekey">traore-etal-2026-reclaiming</identifier>
<identifier type="doi">10.63317/2zgo4ih7o2ch</identifier>
<location>
<url>https://aclanthology.org/2026.rail-1.10/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>96</start>
<end>106</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reclaiming African Voices: Surveying Indigenous Writing Systems for Inclusive NLP
%A Traore, Mamady
%A Le, Ngoc Tan
%A Sadat, Fatiha
%Y Matfunjwa, Muzi
%Y Setaka, Mmasibidi
%Y Mabuya, Rooweither
%Y van Zaanen, Menno
%S Proceedings of Resources for African Indigenous Languages (RAIL) 2026 @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F traore-etal-2026-reclaiming
%X Multilingual NLP has expanded rapidly through large-scale pretraining and cross-lingual transfer, yet this progress remains structurally uneven across writing systems. This survey reframes multilingual NLP around scripts rather than languages, arguing that writing systems constitute an under-theorized axis of computational inequality. Focusing on African scripts — Indigenous (Vai, Ge’ez, Tifinagh), modern (ADLaM, N’Ko), and adapted Arabic-based (Ajami)—we analyze how script properties interact with digital infrastructure, tokenization, and downstream task performance. We organize the literature across four analytical layers: infrastructural (Unicode and input systems), representational (segmentation efficiency and vocabulary allocation), functional (task-level disparities), and epistemic (evaluation bias and the “low-resource” framing). Synthesizing evidence from 47 studies, we show that performance gaps across scripts arise primarily from engineering design choices rather than intrinsic linguistic complexity. We conclude by outlining a research agenda for native multiscript foundation models, including script-aware scaling laws, tokenizer equity metrics, and evaluation reform. We argue that multiscript equity is not a peripheral concern but a structural precondition for genuine multilingual inclusion
%R 10.63317/2zgo4ih7o2ch
%U https://aclanthology.org/2026.rail-1.10/
%U https://doi.org/10.63317/2zgo4ih7o2ch
%P 96-106
Markdown (Informal)
[Reclaiming African Voices: Surveying Indigenous Writing Systems for Inclusive NLP](https://aclanthology.org/2026.rail-1.10/) (Traore et al., RAIL 2026)
ACL