Scientific Publications

Explore our repository of peer-reviewed articles, conference papers, and technical reports driving innovation in Applied AI, Natural Language Processing, and Ethical Technology within the East African context.

Filters:
Sort by:
11 papers
Paper Open Access

CommonLID: Re-evaluating State-of-the-Art Language Identification Performance on Web Data

P Ortiz Suarez, L Burchell, C Arnett, R Mosquera-Gómez, SH Monsalve, T Vaughan, ...

arXiv e-prints / ACL proceedings • 2026

Abstract not provided.

Paper Open Access

Evaluating the Effect of Linguistic Relatedness on Cross-Lingual Transfer in Large Multilingual Automatic Speech Recognition

A Florian, CJ Amol, HK Ombaba, X Cui, B Mwau, BM Kamau, ...

arXiv preprint arXiv:2607.04814 • 2026

Abstract not provided.

Dataset Open Access

AfriVoices-KE: A Multilingual Speech Dataset for Kenyan Languages

L Wanzare, C Amol, E Maina, N Odhiambo, H Kerubo, L Misula, V Oloo, ...

SIGUL 2026 / Workshop proceedings • 2026

Abstract not provided.

Paper Open Access

Tonative: Community-Driven Extension of African Datasets Through Human-AI Collaboration

CJ Amol, S Ibejih

AI for African Languages Conference • 2026

Abstract not provided.

Paper Open Access

Global PIQA: Evaluating Physical Commonsense Reasoning Across 100+ Languages and Cultures

TA Chang, C Arnett, A Eldesokey, A Sadallah, A Kashar, A Daud, ...

arXiv preprint / EMNLP • 2025

Abstract not provided.

Dataset Open Access

Kenyan sign language word-based pose dataset

E Maina, L Wanzare, J Obuhuma, M Ayere, M Kang'ahi, J Okutoyi

Data in Brief • 2025

Abstract not provided.

Dataset Open Access

AfriHate: A Multilingual Collection of Hate Speech and Abusive Language Datasets for African Languages

SH Muhammad, I Abdulmumin, AA Ayele, DI Adelani, IS Ahmad, SM Aliyu, ...

Conference proceedings • 2025

Abstract not provided.

Paper Open Access

Modelling Misinformation in Swahili-English Code-switched Texts

C Amol, L Wanzare, J Obuhuma

International Journal of Information Technology and Computer Science • 2025

Abstract not provided.

Subscribe to our Newsletter