Main content

Can artificial intelligence better serve African languages?

Experts say machines need more data on languages to be able to speak and understand them but African languages lug behind

While 2000 of the world’s languages are African, African languages are barely represented in technology.

Part of the reason for this is that many of these African languages are classed as 'low-resource'.

This means there is a lack of data existing for these languages - and this is the data needed to teach machines how to speak and understand them.

As a result, technology has been unavailable to large swaths of the continent.

However, there are signs that things are starting to change.

This year, Google Translate announced it would be adding 10 more African languages.

Alan Kasujja has been speaking to Dr Ignatius Ezeani, a senior researcher on Natural Language Processing and Nana Ghartey, founder of Ghanaian voice assistance app, Abena, to find out how artificial intelligence can better serve African languages.

Release date:

Available now

13 minutes

Podcast