IGBO DIALECTS AND AI; TOWARDS A DIALECT-AWARE FRAMEWORK
Keywords:
Igbo dialects, dialectal NLP, low-resource languages, artificial intelligence, language developmentAbstract
Artificial intelligence (AI) systems developed for Igbo are trained mainly on Standard (Central) Igbo, although everyday communication occurs through numerous regional varieties. This paper examines how that standardization bias affects the digital vitality and representation of Igbo dialects. It uses a structured descriptive-theoretical review of 18 sources on Igbo dialectology, language ecology, digital vitality, natural language processing, machine translation, and community data governance. The sources are analyzed thematically against four research questions concerning dialect documentation, available digital resources, system performance, and strategies for dialect-aware development. The review finds that Igbo dialects are extensively described in print scholarship but remain poorly represented in machine-readable corpora, speech datasets, input tools, and automated processing systems. IgboAPI provides an important partial lexical resource, yet no complete publicly accessible text-and-speech corpus exists for any dialect. Evidence reviewed also indicate that systems trainedon Standard Igbo perform less effectively on dialectal input, thereby limiting access for dialect speakers. In response, the paper proposes a four-tier framework that combines dialectological classification, language ecology, digital vitality indicators, community-led data collection, and isomorphism-guided transfer learning. The framework prioritizes practical development while retaining every documented variety within the long-term planning horizon. The study concludes that inclusive Igbo AI requires coordinated resource creation, transparent performance testing, and community control over linguistic data.
References
Adelani, D. I., Alabi, J., &Nekoto, W. (2022). Low-resource African language AI: Challenges and opportunities. Journal of African Language Technology, 3(1), 45–67.
Bird, S. (2022). Decolonising computational linguistics. Computational Linguistics, 48(3), 741-768.
Chambers, J. K., &Trudgill, P. (1998). Dialectology (2nd ed.). Cambridge University Press.
Chinagọrọm, L. C. (2010). Linguistic isomorphism and Igbo dialects: Evidence from the Nsụka and Owere dialect clusters [Doctoral dissertation, University of Nigeria, Nsukka].
Emenanjo, E. N. (1996). Olumefula: Asụsụ Igbo na ndụ ndị Igbo. Assumpta Press.
Emezue, C. C., Okoh, I., Mbonu, C., Chukwuneke, C., Lal, D., Ezeani, I., Rayson, P., Onwuzulike, I., Okeke, C., Nweya, G., Ogbonna, B., Oraegbunam, C., Awo-Ndubuisi, E., Osuagwu, A., &Nmezi, O. (2024). The IgboAPI dataset: Empowering Igbo language technologies through multi-dialectal enrichment. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) (pp. 1–12). European Language Resources Association.
Ezeani, I., Onyenwe, I., &Hepple, M. (2020). Building the Igbo-English machine translation corpus. In Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC 2020) (pp. 3456–3463).
Ezikeojiakụ, P. A. (1998). A study of Igbo dialects. Lingua Publishers.
Ezulu, P. (2025). Dialect-aware neural models for low-resource African languages: A case study on Igbo. NeurIPS 2025 Workshop on Generative AI for Education. https://neurips.cc/virtual/2025/loc/san-diego/133953
Haugen, E. (1972). The ecology of language. Stanford University Press.
Ikekeọnwụ, C. I. (2001, November 29). Igbo language and its dialects: A critical appraisal [Paper presentation]. Ahịajọkụ Lecture Colloquium, Owerri, Nigeria.
Inuwa-Dutse, I. (2025). NaijaNLP: A survey of Nigerian low-resource languages. arXiv (arXiv:2502.19784).
Mühlhäusler, P. (1996). Linguistic ecology: Language change and linguistic imperialism in the Pacific region. Routledge.
Nwaozuzu, G. I. (2008). Dialects of the Igbo language. University of Nigeria Press.
Obiwuru, L. C. (2025). Assessing the impact of AI translation systems on Igbo language: A critical discourse analysis. EKETE International Journal of Advanced Research, 3(2).
Onyenwe, I., Uche, C., &Ezeani, I. (2020). Neural tone prediction for Igbo text. In Proceedings of AfricaNLP 2020 (pp. 45–52).
UNESCO Ad Hoc Expert Group on Endangered Languages. (2003). Language vitality and endangerment. UNESCO.
University of Lagos. (2026, February 18). UNILAG champions indigenous languages in the age of artificial intelligence. https://unilag.edu.ng/unilag-champions-indigenous-languages-in-the-age-of-artificial-intelligence
Downloads
Published
Issue
Section
License
Copyright (c) 2026 This is an Open Access article distributed under the terms of the Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, adaptation, and reproduction in any medium, provided that the original work is properly cited.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Authors are permitted to post their work online in institutional/disciplinary repositories or on their own websites. Pre-print versions posted online should include a citation and link to the final published version in Journal of Librarianship and Scholarly Communication as soon as the issue is available; post-print versions (including the final publisher's PDF) should include a citation and link to the journal's website.
