AI in Africa: A bot taught to read messages

Share on facebook
Share on twitter
Share on whatsapp

If you want to fully understand AI , you need to know what is a bot. AI bots are self-learning complex programs that are programmed with Natural Language Processing (NLP) and Machine Learning.

Dossou’s  Mom often sends him voice messages in Fon, a Beninese language, when he has left to study in Russia. However, he does not understand some of the sentences she uses.

“My mother doesn’t know how to write Fon and I don’t speak that language very well, but I do speak French fluently,” Dossou said.

“I often ask my sister to help me understand some of the sentences my mother uses,” he said.

There is no question of improving one’s fon by studying because, like hundreds of other African languages, it is mainly spoken and rarely documented, so that there are few, if any, books to teach grammar and syntax.

Driven by curiosity and fueled by data collected on the Fon thanks to a Bible from Jehovah’s Witnesses, Mr. Dossou and Chris Emezue, a Nigerian friend, have developed a model of language translation by artificial intelligence (AI) that Dossou used to read the voice  messages of his mom in Fon, It is similar to Google Translate, which they named FFR.

They are still working on improving their invention.The two students are part of several AI researchers who use African languages in natural language processing (NLP), a branch of AI used to teach and help computers understand human languages.

Dossou and Emezue
If the world had not stopped following the Covid-19 pandemic, MM. Dossou and Emezue are said to have presented their creation to hundreds of participants at one of the world’s largest AI conferences, the ICLR, which took place this week in the Ethiopian capital, Addis Ababa. It was the first time that the event was held in Africa.Instead of canceling the event, the organizers decided to hold it virtually. AI innovations have been identified as the engine of the “fourth industrial revolution” that will bring dramatic changes to almost every aspect of our lives, including the way we work.Some analysts have called big data that powers AI systems a new oil. For now, Africa is seen as losing out in the role it plays in shaping the future of AI, as the majority of the continent’s 2,000 languages are estimated to be “ scarce resources ”, which means that there is a lack of data about them and / or that what is available has not been indexed and stored in formats that may be useful.

Bridging the language gap with the use of AI

African languages ​​are not taken into account when creating PNA applications such as voice assistants, image recognition software, traffic alert systems and others. But African researchers are working to eliminate this handicap. “We are working to put Africa on the map of NLP and AI research,” said Dr Ignatius Ezeani of the University of Lancaster to the BBC. “If you don’t make your language resources available to the public, free and openly, researchers will not have the data to find creative solutions. We will always have to depend on, say, Google to determine the direction of the search, “said Dr. Ezeani. The conference in Ethiopia was to be an important event for African researchers who, among other difficulties, were denied visas to attend ICLR conferences held in the United States and Canada, which kept them at home. away from global AI conversations.

Leave a Reply

Your email address will not be published. Required fields are marked *