Dealing with the Hard Facts of Low-Resource African NLP

Michael Leventhal, Yacouba Diarra, Nouhoum Coulibaly, Panga Azazia Kamaté, Aymane Dembélé, Madani Amadou Tall, Emmanuel Elise Kone


Abstract
Creating speech datasets, models, and evaluation frameworks for low-resource languages remains challenging given the lack of a broad base of pertinent experience to draw from. This paper reports on the field collection of 612 hours of spontaneous speech in Bambara, a low-resource West African language; the semi-automated annotation of that dataset with transcriptions; the creation of several monolingual ultra-compact and small models using the dataset; and the automatic and human evaluation of their output. We offer practical suggestions for data collection protocols, annotation, and model design, as well as evidence for the importance of performing human evaluation. In addition to the main dataset, multiple evaluation datasets, models, and code are made publicly available.
Anthology ID:
2026.africanlp-main.1
Volume:
Proceedings of the 7th Workshop on African Natural Language Processing (AfricaNLP 2026)
Month:
March
Year:
2026
Address:
Rabat, Morocco
Editors:
Everlyn Asiko Chimoto, Constantine Lignos, Shamsuddeen Muhammad, Idris Abdulmumin, Clemencia Siro, David Ifeoluwa Adelani
Venues:
AfricaNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1–10
Language:
URL:
https://aclanthology.org/2026.africanlp-main.1/
DOI:
Bibkey:
Cite (ACL):
Michael Leventhal, Yacouba Diarra, Nouhoum Coulibaly, Panga Azazia Kamaté, Aymane Dembélé, Madani Amadou Tall, and Emmanuel Elise Kone. 2026. Dealing with the Hard Facts of Low-Resource African NLP. In Proceedings of the 7th Workshop on African Natural Language Processing (AfricaNLP 2026), pages 1–10, Rabat, Morocco. Association for Computational Linguistics.
Cite (Informal):
Dealing with the Hard Facts of Low-Resource African NLP (Leventhal et al., AfricaNLP 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.africanlp-main.1.pdf