A Multilingual African Embedding for FAQ Chatbots
This addresses the need for reliable crisis information in African dialects, though it is incremental as it adapts existing embedding methods.
The paper tackled the problem of scattered and inaccessible official information in African languages by developing a multilingual chatbot for crisis communication, which achieved user satisfaction in a deployed Covid-19 chatbot.
Searching for an available, reliable, official, and understandable information is not a trivial task due to scattered information across the internet, and the availability lack of governmental communication channels communicating with African dialects and languages. In this paper, we introduce an Artificial Intelligence Powered chatbot for crisis communication that would be omnichannel, multilingual and multi dialectal. We present our work on modified StarSpace embedding tailored for African dialects for the question-answering task along with the architecture of the proposed chatbot system and a description of the different layers. English, French, Arabic, Tunisian, Igbo,Yorùbá, and Hausa are used as languages and dialects. Quantitative and qualitative evaluation results are obtained for our real deployed Covid-19 chatbot. Results show that users are satisfied and the conversation with the chatbot is meeting customer needs.