activity
20232026
collaborators

5 papers

cs.CL2026

Concept Direction Reliability Across Languages with Different Tokenizer Fertility

Muhammad Abdullahi Said, Abass Oguntade, Elisha Komolafe +3

Extracted sentiment directions can vary across samples even when downstream sentiment classification remains accurate. To evaluate direction reproducibility, we measure split-half…

cs.CL2025

Automatic Speech Recognition for African Low-Resource Languages: Challenges and Future Directions

Sukairaj Hafiz Imam, Babangida Sani, Dawit Ketema Gete +6

Automatic Speech Recognition (ASR) technologies have transformed human-computer interaction; however, low-resource languages in Africa remain significantly underrepresented in both…

cs.CL2025

HausaNLP: Current Status, Challenges and Future Directions for Hausa Natural Language Processing

Shamsuddeen Hassan Muhammad, Ibrahim Said Ahmad, Idris Abdulmumin +9

Hausa Natural Language Processing (NLP) has gained increasing attention in recent years, yet remains understudied as a low-resource language despite having over 120 million first-l…

cs.CL2025

Who Wrote This? Identifying Machine vs Human-Generated Text in Hausa

Babangida Sani, Aakansha Soy, Sukairaj Hafiz Imam +5

The advancement of large language models (LLMs) has allowed them to be proficient in various tasks, including content generation. However, their unregulated usage can lead to malic…

cs.CL2023

Leveraging Closed-Access Multilingual Embedding for Automatic Sentence Alignment in Low Resource Languages

Idris Abdulmumin, Auwal Abubakar Khalid, Shamsuddeen Hassan Muhammad +5

The importance of qualitative parallel data in machine translation has long been determined but it has always been very difficult to obtain such in sufficient quantity for the majo…