Bringing Stories Alive: Generating Interactive Fiction Worlds
This work addresses the challenge of automating world-building for narrative intelligence tasks, which is incremental by building on existing methods for knowledge graph completion and neural language generation.
The paper tackles the problem of procedurally generating interactive fiction worlds by using story plots to extract and complete knowledge graphs, then guiding a neural language model to generate coherent and interesting text-based worlds, with human evaluations showing competitive performance against rule-based and human-made baselines.
World building forms the foundation of any task that requires narrative intelligence. In this work, we focus on procedurally generating interactive fiction worlds---text-based worlds that players "see" and "talk to" using natural language. Generating these worlds requires referencing everyday and thematic commonsense priors in addition to being semantically consistent, interesting, and coherent throughout. Using existing story plots as inspiration, we present a method that first extracts a partial knowledge graph encoding basic information regarding world structure such as locations and objects. This knowledge graph is then automatically completed utilizing thematic knowledge and used to guide a neural language generation model that fleshes out the rest of the world. We perform human participant-based evaluations, testing our neural model's ability to extract and fill-in a knowledge graph and to generate language conditioned on it against rule-based and human-made baselines. Our code is available at https://github.com/rajammanabrolu/WorldGeneration.