Condita: A state machine like architecture for multi-modal task bots

Conversational Artificial Intelligence (AI) has been a long-standing area of exploration in the research community and has now penetrated both academia and industries with products such as Siri and Alexa. In this work, we present COoking-aNd-DIy-TAsk-based (Condita) ChatBot, a task-oriented dialogue system, for the 2021 Alexa Prize TaskBot Challenge. Condita provides an engaging multi-modal agent that assists users in cooking and home improvement tasks. Our main goal was to generate engaging dialogue and provide an effortless user experience in order to create a memorable, enjoyable experience for users. In this paper, we discuss Condita’s state machine like architecture and analyze the various conversational strategies implemented that allowed us to achieve excellent performance throughout the competition.