An Automated Story Generator of the Old French Epic

All sentences or passages quoted in this report from other people's work have been specifically acknowledged by clear cross-referencing to author, work and page(s). Any illustrations which are not the work of the author of this report have been used with the explicit permission of the originator and are specifically acknowledged. I understand that failure to do this amounts to plagiarism and will be considered grounds for failure in this project and the degree examination as a whole. The field of story generation has existed in cognitive science since 1973 when Klein released the Automatic Novel Writer (Klein et al, 1973) – the first automated story generator. This was later followed by generators which focused on two main approaches – a story-grammar approach (such as Correira, 1980) or a simulation-based approach such as Meehan's (1977) TAIL-SPIN. This project proposes a story generator to model the fixed narrative sub-domain of the Guillaume d'Orange cycle of the Old French Epic (or Chansons de Geste) and in doing so will try to determine which approach produces the most interesting, and authentic epic whilst still preserving its intelligence (Ryan, 1991) as a program. The product of this project is a moderately successful narrative generator which bases its approach on the controlled-simulation model of narrative generators. iii iv III. Acknowledgements I would like to thank Tony Simons for his excellent support and inspiration as a supervisor. I am also very grateful to the generosity of Penny Simons in giving her time to help in my understanding of Old French epics. I would also like to thank my housemates Terry Burke and Ben Palin for their continued support throughout the project.