Highly-Scalable NLP to Answer Questions on COVID-19 WhatsApp Hotline | PyData Global 2021

Highly-Scalable NLP to Answer Questions on South Africa’s COVID-19 WhatsApp Hotline Speaker: Adam Chang Summary Over 10 million people use South Africa’s national COVID-19 WhatsApp hotline, but the service lacked support for users who ask free-form questions. This talk centers on how we built a scalable natural language (NLP) solution that enables users to ask their own questions about vaccines. We’ll discuss various choices behind our model, and how we’ve improved its overall performance and efficiency. Description Over 10 million people use South Africa’s national COVID-19 WhatsApp hotline, but the service previously lacked support for users who ask free-form questions. This talk centers on how we built a scalable natural language processing (NLP) service, so that users can now ask their own questions about COVID-19 vaccines (e.g., “Is the COVID shot safe if I’m having a child?” or “Which vaccine brand is the best?”). While some background in algorithms and machine learning is