Abstract: Text classification is a pivotal challenge in Natural Language Processing (NLP), particularly for underrepresented languages like Bangla, spoken by over 230 million native speakers.

For many African languages there are few written resources online that can be used to train AI. The African Next Voices project is trying to change that by recording underrepresented languages and ...

Classifying geospatial imagery remains a major bottleneck for applications such as disaster response and land-use monitoring-particularly in regions where annotated data is scarce or unavailable.

Voice-based technologies are essential to cater to the hundreds of millions of new smartphone users. However, most of the languages spoken by these new users have little to no labelled speech data.

Agenda 2063 is the blueprint and master plan for transforming Africa into the global powerhouse of the future. It is the strategic framework for delivering on Africa’s goal for inclusive and ...

Abstract: The translation of low-resource languages remains a significant challenge in Natural Language Processing (NLP) due to the scarcity of high-quality parallel data for training machine ...

A new report from the University of Liverpool and the United Nations Migration Agency–International Organization for ...