MAKEBELIEVE: Using Commonsense Knowledge to Generate Stories

This paper introduces MAKEBELIEVE, an interactive story generation agent that uses commonsense knowledge to generate short fictional texts from an initial seed story step supplied by the user. A subset of commonsense de-scribing causality, such as the sentence "a consequence of drinking alcohol is intoxication," is selected from the on-tology of the Open Mind Commonsense Knowledge Base. Binary causal relations are extracted from these sentences and stored as crude trans-frames. By performing fuzzy, creativity-driven inference over these frames, creative "causal chains" are produced for use in story generation. The current system has mostly local pair-wise constraints between steps in the story, though global constraints such as narrative structure are being added.

Authors

• Hugo Liu and Push Singh MIT Media Laboratory

Keywords

No keywords are indexed for this paper.