AAAI Publications, Thirteenth Artificial Intelligence and Interactive Digital Entertainment Conference

Font Size: 
Toward Automated Story Generation with Markov Chain Monte Carlo Methods and Deep Neural Networks
Brent Harrison, Christopher Purdy, Mark O. Riedl

Last modified: 2017-09-19


In this paper, we introduce an approach to automated story generation using Markov Chain Monte Carlo (MCMC) sampling. This approach uses a sampling algorithm based on Metropolis-Hastings to generate a probability distribution which can be used to generate stories via random sampling that adhere to criteria learned by recurrent neural networks. We show the applicability of our technique through a case study where we generate novel stories using an acceptance criteria learned from a set of movie plots taken from Wikipedia. This study shows that stories generated using this approach adhere to this criteria 85%-86% of the time.


MCMC Sampling; Guided Story Generation; Deep Learning

Full Text: PDF