Machine Learning Thesis
Domain-independent narrative content generation.
A lot of work has been done in the area of narrative generation, or how to get computers to write coherently plotted interesting stories. However, most of this work has focused on how to take a corpus of human-authored information, arrange the events and characters in a logical way, and then generate decent prose. To fully achieve narrative intelligence, it is necessary to overcome the necessity of using human-authored input at the beginning of the process. This thesis focuses on learning appropriate narrative events and characters from works of literature, as a human author would, and then assembling a plot graph of these events, which can be traversed based on sequential probability to produce a coherent plot.