Course Catalogue

View Specification Document | Reading List

This course provides a hands-on introduction to conversational interaction. Students will learn about the components involved in a conversational system, the techniques for implementing such a system, and how conversational systems are evaluated. Various forms of conversational interface will be covered, including chatbots, spoken dialogue systems, multimodal dialogue systems, and social robots. During the course, students will implement and evaluate a conversational interactive system.

Two hours lecture per week, one hour practical class per week

Recommended courses (not mandatory): Artificial Intelligence, Computational Social Intelligence, Data Fundamentals, Machine Learning.

These courses are not necessary but will give students additional context to permit a deeper understanding of the content taught in the current course.

None

None

Examination 70%, report 25%, system demo presentation 5%

Reassessments are normally available for all courses, except those which contribute to the Honours classification. For non-Honours courses, students are offered reassessment in all or any of the components of assessment if the satisfactory (threshold) grade for the overall course is not achieved at the first attempt. This is normally grade D3 for undergraduate students and grade C3 for postgraduate students. Exceptionally it may not be possible to offer reassessment of some coursework items, in which case the mark achieved at the first attempt will be counted towards the final course grade. Any such exceptions for this course are described below. 

The report and demo cannot be reassessed because they will both be based on work that will be done during the 10 hours of practical work planned for the course. This work can therefore not be done after the end of the course.

The aim of the course is to survey the theoretical and practical aspects involved in implementing and evaluating conversational interfaces. It introduces the main component tasks involved in a conversational interaction, ranging from speech recognition to output generation, and surveys tools and approaches that can be used for building a conversational system. It also introduces techniques and instruments for testing and evaluating systems.

By the end of this course students will be able to:

■ Review, critically analyse, evaluate and synthesize existing research in the field of conversational interfaces and spoken language processing.

■ Make informed judgments about appropriate methodologies for developing and evaluating conversational interfaces.

■ Implement a conversational interface using a suitable programming language and software tools.

■ Carry out a user evaluation of an implemented conversational system.

■ Explain how the use of multimodal interaction and embodied agents affects the development, deployment, and evaluation of conversational interfaces

Students must submit at least 75% by weight of the components (including examinations) of the course's summative assessment.