Commonsense knowledge

Thematic analysis

World Wide Web

Natural language

Linguistics

Possible world

Philosophy

Virtual world

Knowledge extraction

Cartography

Theoretical computer science

Archaeology

Narrative

Computer science

Natural language generation

Virtual reality

Qualitative research

Natural language processing

Fictional universe

Graph

Thematic map

Geography

Metaverse

Epistemology

Natural (archaeology)

Sociology

Artificial intelligence

Knowledge graph

Human–computer interaction

Social science

History

Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment

Interactive fictions—also called text-based games—are games in which a player interacts with a virtual world purely through textual natural language. In this work, we focus on procedurally generating interactive fiction worlds. Generating these worlds requires (a) referencing everyday and thematic commonsense priors in addition to (b) being semantically consistent, (c) interesting, (d) coherent throughout, all while (e) producing fluent natural language descriptions of places, people, and things. Using existing story plots from books 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 evaluate generated worlds with human-participant studies, comparing our technique against rule-based and human-made baselines

Bringing Stories Alive: Generating Interactive Fiction Worlds