2020

Bringing Stories Alive: Generating Interactive Fiction Worlds

Ammanabrolu, Prithviraj, Cheung, Wesley, Tu, Dan et al.

Understand

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.

An analysis of open information extraction based on semantic role labeling
Janara Christensen, Stephen Soderland, Oren Etzioni, and Mausam · 2011
Earlier work this paper cites.
Crowdsourcing Narrative Intelligence
Boyang Li, Stephen Lee-Urban, Darren Scott Appling, and Mark O. Riedl · 2012
Earlier work this paper cites.
Crowdsourcing open interactive narrative
Matthew Guzdial, Brent Harrison, Boyang Li, and Mark Riedl · 2015
Earlier work this paper cites.
Language Understanding for Text-based Games Using Deep Reinforcement Learning
Karthik Narasimhan, Tejas Kulkarni, and Regina Barzilay · 2015
Earlier work this paper cites.
Demonyms and compound relational nouns in nominal open ie
Harinder Pal and Mausam · 2016
Earlier work this paper cites.
Textworld: A learning environment for text-based games
Original
Marc-Alexandre Côté, Ákos Kádár, Xingdi Yuan, Ben Kybartas, Tavian Barnes, Emery Fine, James Moore, Matthew Hausknecht, Layla El Asri, Mahmoud Adada, et al · 2018
Earlier work this paper cites.
Learning How Not to Act in Text-Based Games
Matan Haroush, Tom Zahavy, Daniel J Mankowitz, and Shie Mannor · 2018
Earlier work this paper cites.
Open information extraction from conjunctive sentences
Swarnadeep Saha and Mausam · 2018
Earlier work this paper cites.

Transfer in deep reinforcement learning using knowledge graphs
Prithviraj Ammanabrolu and Mark Riedl · 2019
Cited alongside, same era.
Playing text-adventure games with graph-based deep reinforcement learning
Prithviraj Ammanabrolu and Mark O. Riedl · 2019
Cited alongside, same era.
Toward automated quest generation in text-adventure games
Prithviraj Ammanabrolu, William Broniec, Alex Mueller, Jeremy Paul, and Mark O Riedl · 2019
Cited alongside, same era.
Generating interactive worlds with text
Original
Angela Fan, Jack Urbanek, Pratik Ringshia, Emily Dinan, Emma Qian, Siddharth Karamcheti, Shrimai Prabhumoye, Douwe Kiela, Tim Rocktaschel, Arthur Szlam, et al · 2019
Cited alongside, same era.
Interactive fiction games: A colossal adventure
Original
Matthew Hausknecht, Prithviraj Ammanabrolu, Marc-Alexandre Côté, and Xingdi Yuan · 2019
Cited alongside, same era.
Nail: A general interactive fiction agent
Original
Matthew Hausknecht, Ricky Loynd, Greg Yang, Adith Swaminathan, and Jason D. Williams · 2019
Cited alongside, same era.
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
Original
Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut · 2019
Cited alongside, same era.
Language models are unsupervised multitask learners
Alec Radford, Jeff Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever · 2019
Cited alongside, same era.

Are red roses red? evaluating consistency of question-answering models
Marco Tulio Ribeiro, Carlos Guestrin, and Sameer Singh · 2019
Later among the works it cites.
CTRL: A Conditional Transformer Language Model for Controllable Generation
Original
Nitish Shirish Keskar, Bryan McCann, Lav R. Varshney, Caiming Xiong, and Richard Socher · 2019
Later among the works it cites.
Learning to speak and act in a fantasy text adventure game
Jack Urbanek, Angela Fan, Siddharth Karamcheti, Saachi Jain, Samuel Humeau, Emily Dinan, Tim Rocktäschel, Douwe Kiela, Arthur Szlam, and Jason Weston · 2019
Later among the works it cites.
Interactive narrative generation using location and genre specific context
Jon Womack and William Freeman · 2019
Later among the works it cites.
Comprehensible context-driven text game playing
Original
Xusen Yin and Jonathan May · 2019
Later among the works it cites.
Interactive language learning by question answering
Xingdi Yuan, Marc-Alexandre Côté, Jie Fu, Zhouhan Lin, Christopher Pal, Yoshua Bengio, and Adam Trischler · 2019
Later among the works it cites.
Graph constrained reinforcement learning for natural language action spaces
Prithviraj Ammanabrolu and Matthew Hausknecht · 2020
Closest in time.

alphaXiv searches the wider corpus for related work and actual follow-ups.

alphaXiv is searching for related work…

Reading the bibliography…