Access to information in the desired language has been a challenge in many multilingual and multidialectal countries for a long time. This issue has been even more critical during the coronavirus disease (COVID-19) pandemic because people’s lives and safety depended on receiving comprehensible information at the right time. Translators without Borders (TWB) developed multilingual, conversational chatbots to provide real time, reliable information on COVID-19 to the users in their own language. The chatbots were developed in the Democratic Republic of the Congo in partnership with the International Federation of Red Cross and Red Crescent Societies (IFRC) and Kinshasa Digital; and in the Federal Republic of Nigeria in partnership with Mercy Corps.

The chatbots operate on multiple platforms (Facebook, Telegram and WhatsApp) and use natural language processing, which gives computers the ability to understand text in much the same way humans can. [i] This enables users to ask questions in their own words and receive relevant responses in the same language. These chatbots thus convey locally relevant, multimedia content to audiences, including those who speak marginalized languages or have lower literacy levels. Furthermore, the responsible team analyses the questions users ask; the results of which support humanitarian responders to identify people’s information needs and tailor their communication efforts. The information is also used to develop language models that can be used in a range of applications like machine translation as well as certain components of an interactive voice response solution for local languages.