Human-Machine Dialogue

Master in Artificial Intelligence Systems

Register to the moodle page of this course to receive updated information re lecture video links, assignments, notices and general information
Lectures will be live and you will all get granted access to the classroom ( both physical and virtual ). Highly recommended in-person attendance.

Robots that can talk or chat with humans are becoming pervasive in many industry and consumer domains. Artificial Intelligent Systems (AIS) using natural language can interact with human and operate in command-and-control, information retrieval or cooperative decision-support tasks. In this course we review the basic principles of human computer interaction and then address the fundamental structures of a human conversation. We derive the concepts from conversation linguistics, discourse analysis to describe computational dialogue models, dialogue system architectures and their evaluation. In the second part of the course we provide methodologies for the design of conversational agents, data-driven training, design tools and a project-based lab addressing real use cases.

Read the

=======Lecture Topics, Slides, Lab============

Below the topics that will be covered by the course. The course is project-based, meaning
that the students' requirement is to design, train and develop a human-machine dialogue system by
the end of the course whether the "touch point" is a smartphone, desktop web browser, a smart speaker,
a smart watch, in-car "invisible" interface. The course is based on lecture and labs sessions.

  1. Course Description (Incl. Assignments and Student Evaluation)
  2. Basics of Human Computer Interaction
  3. Conversational Design ( 1, 2, 3 )
  4. Linguistics of Conversations
  5. Emotions in Dialogue ( Lab )
  6. Dialogue Models
  7. Natural Language Generation
  8. Machine Learning models for Conversational Models
  9. Reinforcement Learning
  10. Dialogue Evaluation
  11. Ethics and Privacy in Human-Machine Dialogue Systems
  12. Tools and frameworks for designing, training and developing Human-Machine Dialogue Systems