Ife Adebara is on a mission to make technology accessible to all people on the African continent — by making their language available in the technology they use.
“Someone who speaks a minority language has to put their language aside to be able to get technology in English for example,” said Adebara, a programmer and scholar in the linguistics department at the University of British Columbia.
“Over time the use of the language starts to decline and this can have long-term consequences of language risk … we need to mitigate this.”
Adebara says AI technology is advancing rapidly but is leaving behind people who speak languages other than English.
Her project, called Afrocentric Natural Language Processing, works to create awareness, tools and programs that are accessible to members of the public who speak an African language, including Swahili and Zulu.
So far, he says, the team has released two online language recognition programs called SERENGETI and AfroLID.
In view of her interview at The Early EditionAdebara spoke with CBC’s Ali Pitargue to share more about her work and the need to make technology inclusive.
The following interview has been edited for clarity and length.
What is the AI and African Languages Initiative?
The concept seeks to bring technology to Africans in their native languages.
This includes developing these components, creating models of artificial intelligence and deploying it to the African people so that they can interact with the technology in the languages they are most comfortable with, which is usually their indigenous languages.
What languages do you work in?
There are more than 2,000 languages in Africa. So right now I’m working on about 517 of them, which are spoken by 50 of the 54 countries in Africa.
This number is increasing as more languages are added to the list I work with. The goal is to be able to reach as many languages as possible on the African continent.
These languages are often referred to as low resource languages. Can you elaborate more on this and the challenges involved?
Low-resource languages are languages that do not have sufficient data to build classical language models for artificial intelligence.
So the challenge with these types of languages is that performance is usually lower than high-resource languages like English, French, and some other Indo-European languages.
One approach I’ve used to mitigate this challenge is to combine multiple languages into the same model. This way the model learns from multiple languages and the data set becomes larger than it was before and the performance is a bit better.
But it still needs to be solved, because if we’re going to get to near-human accuracy, then we need more data to be able to do that.
Why is it important to ensure that African languages are not left behind in the development of these technologies?
There are two reasons why this is important. The first is that more than a billion people in Africa, which is about 17 percent of the world’s population, are excluded from global conversations in their indigenous languages.
They don’t listen to what others say and we don’t listen to what they say.
The other thing is that for many African languages, their grammatical features are very different and sometimes unique only to the African continent.
If we build language technology and exclude African languages, the models and technologies do not learn certain language features. Which is also not a good thing, because they are not flexible to various grammatical features that exist in human language.
What do you hope this project will achieve overall?
I hope the technologies become available and accessible to the average African. This would certainly have long-term implications for education.
They can access information on the web in their language, either translated into their language or translated from another language. I see people accessing health information in their own language or being able to use Google Maps.
For more stories about the experiences of Black Canadians – from anti-Black racism to success stories within the Black community – check out Being Black in Canada, a CBC project Black Canadians can be proud of. You can read more stories here.
(CBC)