Bringing Stories Alive: Generating Interactive Fiction Worlds

TL;DR

This paper introduces a method for procedurally generating interactive fiction worlds by extracting and completing knowledge graphs to guide neural language models, enabling coherent and thematically consistent text-based worlds.

Contribution

It presents a novel approach combining knowledge graph completion with neural language generation for interactive fiction world building, leveraging thematic priors.

Findings

Neural model effectively fills in knowledge graphs with thematic information.

Generated worlds are coherent and thematically consistent according to human evaluations.

Outperforms rule-based and human-made baselines in quality and consistency.

Abstract

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.