Natural Language Generation (NLG) systems generate texts in English and other human languages which communicate and summarise data. Previous research has shown that NLG summaries are often more effective at communicating data than visualisations, and there is growing commercial interest in using NLG in a number of contexts, such as business intelligence (BI).
The goal of this PhD project is to develop a better empirical understanding of when NLG texts are more effective than information visualisations, and when they are not; and also of how to best combine NLG and information graphics. We know that at a high level this depends on context, user, and type of information being communicated, but we don’t have detailed models which predict when NLG is useful and when it is not. We also don’t know how to best combine NLG and information graphics.
The project will involve building NLG and information visualisation systems in a few domains, such as weather forecasting and business intelligence, and running experiments to assess how effectively users understand these presentations, and how effectiveness depends on context and the characteristics of the user.
The successful candidate will have or expect to have a UK Honours Degree at 2.1 (or equivalent) in Computing Science or related area; Psychology.
Candidates should either have a solid degree in computing and some knowledge of psychology, or a solid degree in psychology with a good understanding of computing.
APPLICATION PROCEDURE: this project is advertised in relation to the research areas of the discipline of Computing Science. Formal applications can be completed online: https://www.abdn.ac.uk/pgap/login.php You should apply for Degree of Doctor of Philosophy in Computing Science, to ensure that your application is passed to the correct person for processing. NOTE CLEARLY THE NAME OF THE SUPERVISOR and EXACT PROJECT TITLE ON THE APPLICATION FORM.
Informal inquiries can be made to Professor E Reiter ([email protected]) with a copy of your curriculum vitae and cover letter indicating your interest in the project and why you wish to undertake it. All general enquiries should be directed to the Postgraduate Research School ([email protected])
There is no funding attached to this project, it is for self-funded students only.