Generate Believable Causal Plots with User Preferences Using Constrained Monte Carlo Tree Search

Authors

  • Von-Wun Soo National Tsing Hua University
  • Chi-Mou Lee National Tsing Hua University
  • Tai-Hsun Chen National Tsing Hua University

DOI:

https://doi.org/10.1609/aiide.v12i1.12875

Keywords:

Fabula elements, causal story plots, constrained Monte Carlo Tree Search, user preference, believable story generation

Abstract

We construct a large scale of causal knowledge in term of Fabula elements by extracting causal links from existing common sense ontology ConceptNet5. We design a Constrained Monte Carlo Tree Search (cMCTS) algorithm that allows users to specify positive and negative concepts to appear in the generated stories. cMCTS can find a believable causal story plot. We show the merits by experiments and discuss the remedy strategies in cMCTS that may generate incoherent causal plots.

Downloads

Published

2021-06-25

How to Cite

Soo, V.-W., Lee, C.-M., & Chen, T.-H. (2021). Generate Believable Causal Plots with User Preferences Using Constrained Monte Carlo Tree Search. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 12(1), 218-224. https://doi.org/10.1609/aiide.v12i1.12875