Machine learning and the use of artificial intelligence (AI) are opening new doors of opportunity, but as a new study points out, that’s only true if you speak English, French, or one of the other common languages used in products like ChatGPT.

Now, there’s a new effort to ensure that speakers of Shona, Hausa, Xhosa, Kiswahili and other African languages will have the same kind of access to the technology.

“It doesn’t make sense to me that there are limited AI tools for African languages,” says Kathleen Siminyu, above, the Kenya-based tech leader whose work at the Masakhane Research Foundation is focused on making accessible AI tools for those who speak African languages.

“Inclusion and representation in the advancement of language technology is not a patch you put at the end — it’s something you think about up front.”

Siminyu is first author of a new study, published Friday in the Cell Press journal Patterns, that lays out a roadmap for ensuring better AI-driven tools for African languages. Foundational to the project is making sure that data sets for specific languages are available for training computers to master the African languages.

“There is a need to support African content creation. This includes building basic tools such as dictionaries, spell checkers, and keyboards for African languages and removing financial and administrative barriers for translating government communications to multiple national languages, which includes African languages,” the paper authors said.

Next, the team plans to expand the study and address barriers that may hinder people’s access to the technology. The findings may also pave the way to preserve indigenous African languages.

There are gaps even among their own members, they said. “All the researchers of this work are Anglophone, and so Francophone and Lusophone African stakeholders from the relevant groups need to be explicitly included,” they added.

Image: Masakhane Research Foundation