Bringing Stories Alive: Generating Interactive Fiction Worlds

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 this https URL.

[1]  Lav R. Varshney,et al.  CTRL: A Conditional Transformer Language Model for Controllable Generation , 2019, ArXiv.

[2]  Jason Weston,et al.  Generating Interactive Worlds with Text , 2019, AAAI.

[3]  Mark O. Riedl,et al.  Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning , 2018, NAACL.

[4]  Oren Etzioni,et al.  An analysis of open information extraction based on semantic role labeling , 2011, K-CAP '11.

[5]  Regina Barzilay,et al.  Language Understanding for Text-based Games using Deep Reinforcement Learning , 2015, EMNLP.

[6]  Jason Weston,et al.  Learning to Speak and Act in a Fantasy Text Adventure Game , 2019, EMNLP.

[7]  Jonathan May,et al.  Comprehensible Context-driven Text Game Playing , 2019, 2019 IEEE Conference on Games (CoG).

[8]  Matthew J. Hausknecht,et al.  Interactive Fiction Games: A Colossal Adventure , 2020, AAAI.

[9]  Mark O. Riedl,et al.  Toward Automated Quest Generation in Text-Adventure Games , 2019, CCNLG.

[10]  Harinder Pal,et al.  Demonyms and Compound Relational Nouns in Nominal Open IE , 2016, AKBC@NAACL-HLT.

[11]  Kevin Gimpel,et al.  ALBERT: A Lite BERT for Self-supervised Learning of Language Representations , 2019, ICLR.

[12]  Jon Womack,et al.  Interactive Narrative Generation Using Location and Genre Specific Context , 2019, ICIDS.

[13]  Shie Mannor,et al.  Learning How Not to Act in Text-based Games , 2018, ICLR.

[14]  Christopher Joseph Pal,et al.  Interactive Language Learning by Question Answering , 2019, EMNLP.

[15]  Matthew J. Hausknecht,et al.  NAIL: A General Interactive Fiction Agent , 2019, ArXiv.

[16]  Boyang Li,et al.  Crowdsourcing Open Interactive Narrative , 2015, FDG.

[17]  Mark O. Riedl,et al.  Transfer in Deep Reinforcement Learning Using Knowledge Graphs , 2019, EMNLP.

[18]  Ilya Sutskever,et al.  Language Models are Unsupervised Multitask Learners , 2019 .

[19]  Sameer Singh,et al.  Are Red Roses Red? Evaluating Consistency of Question-Answering Models , 2019, ACL.

[20]  Matthew J. Hausknecht,et al.  TextWorld: A Learning Environment for Text-based Games , 2018, CGW@IJCAI.

[21]  Mausam,et al.  Open Information Extraction from Conjunctive Sentences , 2018, COLING.

[22]  Matthew J. Hausknecht,et al.  Graph Constrained Reinforcement Learning for Natural Language Action Spaces , 2020, ICLR.

[23]  Mark O. Riedl,et al.  Crowdsourcing Narrative Intelligence , 2012 .