Dialogue Generation in Interactive Narratives: investigating automatic generation of narratively meaningful dialogues between a virtual character and a human

Interactive narrative techniques should be made compatible with the requirements of dialogue generation to support some of the aesthetic components of traditional media (intended as including humour, witticisms, etc.), however the challenges ahead remain complex.

This project aims to investigate new methodologies for the purpose of automatic generation of narratively meaningful dialogues between a virtual character and a human. We will explore a range of approaches at the interface between affective embodied conversational agents and interactive storytelling for a natural interaction with a human interlocutor. One of the remaining challenges in narrative dialogue generation is how a conversational agent can adapt to its interlocutor by means of modifying its dialogue intentions and information provisions as part of the on-going narrative context. This project will explore and evaluate existing techniques in affective computing, agent-based communication and narrative systems related to the generation of real-time interactive conversations between a virtual agent and a human, as well as devising specific approaches through the development of a prototype which will provide the test-bed for a large-scale user evaluation for validation.

How to apply: Applications are made via our website using the Apply Online button below. If you have an enquiry about this project please contact us via the Email NOW button below, however your application will only be processed once you have submitted an application form as opposed to emailing your CV to us.

The MRes Fee Waive Scholarships are open to UK & EU candidates, who must demonstrate outstanding qualities and be motivated to complete an MRes in 12 months full-time.

Candidate must have a degree in a field connected to application design such as Computer Science, Software Engineering, Game Design, Games Programming, or a related discipline.

The successful applicants must have a proven previous academic excellence (first class honours or equivalent). An IELTS (Academic) score of 6.5 minimum (or equivalent) is essential for candidates for whom English is not their first language.

In addition to satisfying the basic entry criteria, BU will look closely at the qualities, skills and background of each candidate and what they can bring to their chosen research project in order to ensure successful completion.