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.

The final grade of the course consists of the following components:

• Digital Exam (weighting 30%)

• Group Report: Group report on the design, implementation, and evaluation of a conversational agent (weighting 70%)

• Group Assignment 1: group lab exercise - memory (pass/fail)

• Group Assignment 2: group lab exercise - perception (pass/fail)

• Group Assignment 3: group lab exercise - evaluation (pass/fail)

The group lab exercises contribute to the group report.

Final grade calculation = 0.3 * Digital Exam + 0.7 * Group Report + Pass/Fail * Group Assignment 1 + Pass/Fail * Group Assignment 2 + Pass/Fail * Group Assignment 3

A passing final grade for the course can only be earned when for all components at least a 5.0 is earned, and the weighted final grade is at least a 5.8.

In case of an insufficient final result, repair options may exist in accordance with Article 17A, Times and number of examinations, sub 1, of the Teaching and Examination Regulations, for:

• Digital Exam: Resit opportunity

• Group Report: Repair opportunity

• Group Assignment 1: Repair opportunity

• Group Assignment 2: Repair opportunity

• Group Assignment 3: Repair opportunity

Disclaimer: information may change depending on unforeseen circumstances or measures (see: TER Art 2, sub 5).