Elamur Research⌕
☰
home / papers / 2026 / Reclaiming African Voices: Surveying Indigenous Writing Systems for Inclusive NLP

Reclaiming African Voices: Surveying Indigenous Writing Systems for Inclusive NLP

Paper · 2026 · Mamady Traore, Ngoc Tan Le and Fatiha Sadat

Summary

This survey argues that multilingual NLP should be analysed by writing system, not only by language, because current pipelines implicitly favour the Latin script. The authors focus on three kinds of African scripts: long-established Indigenous ones (Vai, Ge'ez, Tifinagh), recently invented ones (ADLaM, N'Ko) and Arabic-derived Ajami. They ran a structured literature review across ACL Anthology venues, AfricaNLP workshops, arXiv preprints and other databases. They then coded the selected studies along four layers: infrastructure (Unicode, keyboards, fonts), representation (tokenization, vocabulary share), function (task results in MT, NER, sentiment, arithmetic, HTR) and epistemics (data sovereignty, evaluation bias, the "low-resource" framing). Their synthesis finds that gaps between scripts come mainly from engineering decisions, such as fragmenting tokenizers, encoding imbalance and skewed training samples, rather than from inherent linguistic difficulty. This makes the problem addressable by design. The paper closes with an agenda for native multiscript foundation models, built around script-aware scaling laws, tokenizer fairness metrics and evaluation reform.

Key points

  • The final review corpus contains N = 47 studies, mostly from 2020–2026. Each was coded with an extraction matrix and assigned to one or more of four layers (infrastructural, representational, functional, epistemic).
  • The scripts covered also include Bamum and Osmanya. Wolofal (Wolof Ajami) serves as a case study of digraphia and of the missing Ajami-specific OCR.
  • Work by Petrov et al. (2023) and by Asprovska and Hunter (2024) shows that encoding identical material in some scripts can take as many as 13× more tokens.
  • Reddy et al. (2026) report a "script tax": LLM arithmetic accuracy falls when numerals appear in ADLaM, N'Ko or Osmanya instead of Hindu-Arabic digits.
  • The authors acknowledge two limitations: few studies treat African scripts as a primary variable, and the review relies mainly on Anglophone venues.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Université du Québec à MontréalMontreal · Canada2 works · 120 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksLiterature and Literary Theory · 519 works

Cite

Cite as Mamady Traore, Ngoc Tan Le and Fatiha Sadat. 2026. Reclaiming African Voices: Surveying Indigenous Writing Systems for Inclusive NLP. Proceedings of Resources for African Indigenous Languages (RAIL) 2026 @ LREC 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/2zgo4ih7o2ch

@inproceedings{traore2026reclaiming,
  title = {{Reclaiming African Voices: Surveying Indigenous Writing Systems for Inclusive NLP}},
  author = {Mamady Traore, Ngoc Tan Le and Fatiha Sadat},
  booktitle = {Proceedings of Resources for African Indigenous Languages (RAIL) 2026 @ LREC 2026},
  year = {2026},
  doi = {10.63317/2zgo4ih7o2ch},
  url = {https://doi.org/10.63317/2zgo4ih7o2ch}
}

References

41 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Ifeoluwanimi Adebara. 2024. Towards Afrocentric natural language processing. Ph.D. thesis, University of British Columbia. ↗
  2. Orevaoghene Ahia, Sachin Kumar, Hila Gonen, Valentin Hofmann, Tomasz Limisiewicz, Yulia Tsvetkov, and Noah A. Smith. 2024. MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization. Advances in Neural Information Processing Systems, 37:47790–47814.
  3. Jesujoba Oluwadara Alabi, Michael A. Hedderich, David Ifeoluwa Adelani, and Dietrich Klakow. 2025. Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 27807–27841, Suzhou, China. Association for Computational Linguistics. find
  4. Marijana Asprovska and Nathan Hunter. 2024. The Tokenization Problem: Understanding Generative AI’s Computational Language Bias. Ubiquity Proceedings, 4(1). ↗
  5. Jesse Atuhurra, Hiroyuki Shindo, Hidetaka Kamigaito, and Taro Watanabe. 2024. Introducing Syllable Tokenization for Low-resource Languages: A Case Study with Swahili. ArXiv:2406.15358 [cs]. ↗
  6. Deborah Bach. 2019. Ibrahima & Abdoulaye Barry: How a new alphabet is helping an ancient people write its own future. Microsoft New Zealand News Centre. find
  7. Lukas Edman, Helmut Schmid, and Alexander Fraser. 2025. EXECUTE: A Multilingual Benchmark for LLM Token Understanding. ArXiv:2505.17784 [cs] version: 1. ↗
  8. Chris Chinenye Emezue. 2026. Improving language models for underserved languages and communities. Ph.D. thesis, Université de Montréal. ↗
  9. Goodwill Erasmo Ndomba, Medard Edmund Mswahili, and Young-Seob Jeong. 2025. Tokenizers for African Languages. IEEE Access, 13:1046–1054. ↗
  10. Fitsum Gaim and Jong C. Park. 2025. Natural Language Processing for Tigrinya: Current State and Future Directions. ArXiv:2507.17974 [cs]. ↗
  11. Kevin Graaf. 2025. Carving Text at Its Joints: A New Perspective on Writing and Computers. In Proceedings of the 2025 ACM SIGPLAN International Symposium on New Ideas, New Paradigms, and Reflections on Programming and Software, Onward! ’25, pages 194–203, New York, NY, USA. Association for Computing Machinery. find
  12. Kedir Yassin Hussen, Walelign Tewabe Sewunetie, Abinew Ali Ayele, Sukairaj Hafiz Imam, Shamsuddeen Hassan Muhammad, and Seid Muhie Yimam. 2025. The State of Large Language Models for African Languages: Progress and Challenges. ArXiv:2506.02280 [cs]. ↗
  13. Vani Kanjirangat, Tanja Samardzic, Ljiljana Dolamic, and Fabio Rinaldi. 2025. Tokenization and Representation Biases in Multilingual Models on Dialectal NLP Tasks. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 23992–24010, Suzhou, China. Association for Computational Linguistics. ↗
  14. Alex Kasonde. 2025. The long march to Unicode: a digital approach to variability in Icibemba orthography. Cogent Arts & Humanities, 12(1):2477347. _eprint: https://doi.org/10.1080/23311983.2025.2477347. ↗
  15. Piers Kelly. 2018. The invention, transmission and evolution of writing: Insights from the new scripts of West Africa. Paths into Script Formation in the Ancient Mediterranean. ISBN: 9788871408989. ↗
  16. Ngoc Tan Le, Ali Mijiyawa, Abdoulahat Leye, and Fatiha Sadat. 2025. The Best of Both Worlds: Exploring Wolofal in the Context of NLP. In Proceedings of the 1st Workshop on NLP for Languages Using Arabic Script, pages 1–6, Abu Dhabi, UAE. Association for Computational Linguistics. find
  17. Yihong Liu, Haotian Ye, Chunlan Ma, Mingyang Wang, and Hinrich Schuetze. 2025. LangSAMP: Language-Script Aware Multilingual Pretraining. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1743–1770, Vienna, Austria. Association for Computational Linguistics. find
  18. Francois Rolihlahla Meyer. 2025. Subword segmental neural language generation for Nguni languages. Ph.D. thesis, University of Cape Town. find
  19. Shahid Minhas and Abiodun Salawu. 2024. Strategic Frameworks for the Empowerment of African Languages: Policy, Practice and Prospects. Forum for Linguistic Studies, 6(6):753–766. ↗
  20. Shamsuddeen Hassan Muhammad, Idris Abdulmumin, Abinew Ali Ayele, Nedjma Ousidhoum, David Ifeoluwa Adelani, Seid Muhie Yimam, Ibrahim Sa’id Ahmad, Meriem Beloucif, Saif M. Mohammad, Sebastian Ruder, Oumaima Hourrane, Pavel Brazdil, Alipio Jorge, Felermino Dário Mário António Ali, Davis David, Salomey Osei, Bello Shehu Bello, Falalu Ibrahim, Tajuddeen Gwadabe, Samuel Rutunda, Tadesse Belay, Wendimu Baye Messelle, Hailu Beshada Balcha, Sisay Adugna Chala, Hagos Tesfahun Gebremichael, Bernard Opoku, and Stephen Arthur. 2023. AfriSenti: A Twitter Sentiment Analysis Benchmark for African Languages. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 13968–13981, Singapore. Association for Computational Linguistics. ↗
  21. Shamsuddeen Hassan Muhammad, Nedjma Ousidhoum, Idris Abdulmumin, Jan Philip Wahle, Terry Ruas, Meriem Beloucif, Christine de Kock, Nirmal Surange, Daniela Teodorescu, Ibrahim Said Ahmad, David Ifeoluwa Adelani, Alham Fikri Aji, Felermino D. M. A. Ali, Ilseyar Alimova, Vladimir Araujo, Nikolay Babakov, Naomi Baes, Ana-Maria Bucur, Andiswa Bukula, Guanqun Cao, Rodrigo Tufiño, Rendi Chevi, Chiamaka Ijeoma Chukwuneke, Alexandra Ciobotaru, Daryna Dementieva, Murja Sani Gadanya, Robert Geislinger, Bela Gipp, Oumaima Hourrane, Oana Ignat, Falalu Ibrahim Lawan, Rooweither Mabuya, Rahmad Mahendra, Vukosi Marivate, Alexander Panchenko, Andrew Piper, Charles Henrique Porto Ferreira, Vitaly Protasov, Samuel Rutunda, Manish Shrivastava, Aura Cristina Udrea, Lilian Diana Awuor Wanzare, Sophie Wu, Florian Valentin Wunderlich, Hanif Muhammad Zhafran, Tianhui Zhang, Yi Zhou, and Saif M. Mohammad. 2025. BRIGHTER: BRIdging the Gap in Human-Annotated Textual Emotion Recognition Datasets for 28 Languages. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8895–8916, Vienna, Austria. Association for Computational Linguistics. ↗
  22. Jessica Ojo, Odunayo Ogundepo, Akintunde Oladipo, Kelechi Ogueji, Jimmy Lin, Pontus Stenetorp, and David Ifeoluwa Adelani. 2025. AfroBench: How Good are Large Language Models on African Languages? In Findings of the Association for Computational Linguistics: ACL 2025, pages 19048–19095, Vienna, Austria. Association for Computational Linguistics. find
  23. Ugochi Okafor. 2025. Multilingual NLP for African Healthcare: Bias, Translation, and Explainability Challenges. In Proceedings of the Sixth Workshop on African Natural Language Processing (AfricaNLP 2025), pages 221–229, Vienna, Austria. Association for Computational Linguistics. ↗
  24. Jeffrey Otoibhi, Oduguwa Damilola, and Okpare David. 2025. SabiYarn: Advancing Low Resource Languages with Multitask NLP Pretraining. In Proceedings of the Sixth Workshop on African Natural Language Processing (AfricaNLP 2025), pages 95–107, Vienna, Austria. Association for Computational Linguistics. find
  25. Aleksandar Petrov, Emanuele La Malfa, Philip Torr, and Adel Bibi. 2023. Language Model Tokenizers Introduce Unfairness Between Languages. Advances in Neural Information Processing Systems, 36:36963–36990.
  26. Jenalea Rajab. 2022. Effect of Tokenisation Strategies for Low-Resourced Southern African Languages. In 3rd Workshop on African Natural Language Processing. find
  27. Varshini Reddy, Craig W. Schmidt, Seth Ebner, Adam Wiemerslage, Yuval Pinter, and Chris Tanner. 2026. The Effect of Scripts and Formats on LLM Numeracy. ArXiv:2601.15251 [cs]. ↗
  28. Mamadou Youry Sall. 2020. African Ajami: The Case of Senegal. In Jamaine M. Abidogun and Toyin Falola, editors, The Palgrave Handbook of African Education and Indigenous Knowledge, pages 545–557. Springer International Publishing, Cham. ↗
  29. Chen Shani, Yuval Reif, Nathan Roll, Dan Jurafsky, and Ekaterina Shutova. 2026. The Roots of Performance Disparity in Multilingual Language Models: Intrinsic Modeling Difficulty or Design Choices? ArXiv:2601.07220 [cs]. ↗
  30. Logan David Simpson. 2025. Modern Indigenous writing systems: From inception to Unicode. Ph.D. thesis, Queen Mary University of London. find
  31. Hailay Kidu Teklehaymanot, Gebrearegawi Gidey, and Wolfgang Nejdl. 2025. Low-Resource English-Tigrinya MT: Leveraging Multilingual Models, Custom Tokenizers, and Clean Evaluation Benchmarks. ArXiv:2509.20209 [cs]. ↗
  32. Hailay Kidu Teklehaymanot and Wolfgang Nejdl. 2025. Tokenization Disparities as Infrastructure Bias: How Subword Systems Create Inequities in LLM Access and Efficiency. ArXiv:2510.12389 [cs]. ↗
  33. Alex de Voogt. 2014. The Cultural Transmission of Script in Africa: the presence of syllabaries. International Journal of Writing Systems: SCRIPTA. find
  34. Kaveh Waddell. 2016. The Alphabet That Will Save a People From Disappearing. The Atlantic. Section: Technology. find
  35. Orgest Xhelili, Yihong Liu, and Hinrich Schuetze. 2024. Breaking the Script Barrier in Multilingual Pre-Trained Language Models with Transliteration-Based Post-Training Alignment. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 11283–11296, Miami, Florida, USA. Association for Computational Linguistics. find
  36. Weihao Xuan, Rui Yang, Heli Qi, Qingcheng Zeng, Yunze Xiao, Aosong Feng, Dairui Liu, Yun Xing, Junjue Wang, Fan Gao, Jinghui Lu, Yuang Jiang, Huitao Li, Xin Li, Kunyu Yu, Ruihai Dong, Shangding Gu, Yuekang Li, Xiaofei Xie, Felix Juefei-Xu, Foutse Khomh, Osamu Yoshie, Qingyu Chen, Douglas Teodoro, Nan Liu, Randy Goebel, Lei Ma, Edison Marrese-Taylor, Shijian Lu, Yusuke Iwasawa, Yutaka Matsuo, and Irene Li. 2025. MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 1513–1532, Suzhou, China. Association for Computational Linguistics. ↗
  37. Nan Yan and Cheng Xu. 2024. Decolonizing African NLP: A Survey on Power Dynamics and Data Colonialism in Tech Development. In 5th Workshop on African Natural Language Processing. find
  38. Oreen Yousuf, Abdulmalik Aminu, Musa Salih Muhammad, Bashir Usman, Mustapha Kurfi Hashim, Joakim Nivre, Beáta Megyesi, and Christian Høgel. 2026. A Handwritten Text Recognition Dataset for Ajami Manuscripts in Fulfulde and Hausa. In Document Analysis and Recognition – ICDAR 2025, pages 620–637, Cham. Springer Nature Switzerland. find
  39. Isabelle A. Zaugg. 2020. Digital Inequality and Language Diversity: An Ethiopic Case Study. In Massimo Ragnedda and Anna Gladkova, editors, Digital Inequalities in the Global South, pages 247– 267. Springer International Publishing, Cham. ↗
  40. Isabelle A. Zaugg, Anushah Hossain, and Brendan Molloy. 2022. Digitally-disadvantaged languages. Internet Policy Review, 11(2):1–11. ↗
  41. Tolúlp Ògúnrmí, Wilhelmina Onyothi Nekoto, and Saron Samuel. 2023. Decolonizing NLP for “Low-resource Languages”: Applying Abebe Birhane’s Relational Ethics. GRACE: Global Review of AI Community Ethics, 1(1). find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/traore-2026-reclaiming-african-voices-surveying-indigenous/