Conversational Agents

Chatbots, embodied and conversational virtual agents, and social robots are becoming more and more popular. Many people are owning an Alexa, Cortana or Echo or are talking to their virtual assistant on their phone. Indeed, such technologies have the potential of making our lives easier and relieve people from the more repetitive tasks. For example, it is imaginable that such systems are being used for financial applications by helping customers with frequently asked questions but also to advise them on in the long term more impactful decisions such as their pension plans. Further applications can be imagined in the area of healthcare and education, some of which are already in existence today.

In this course, attention will be given to different verbal and nonverbal behavioral characteristics of conversation and embodied interaction, such as, intonation, gaze and gestures that humans show when communicating with both other people and machines. This behavior is then related to different multimodal dialogue functions, including turn-taking, addressing others, and backchanneling, that give shape to the communication process. Topics on interaction with embodied agents and how to design memory models for conversational interaction are also discussed. Students apply this knowledge through the design, development, and evaluation of an embodied conversational agent application that uses a memory model to interact.