Toward Automated Story Generation with Markov Chain Monte Carlo Methods and Deep Neural Networks

Brent Harrison; Christopher Purdy; Mark O. Riedl

doi:10.1609/aiide.v13i2.13003

Toward Automated Story Generation with Markov Chain Monte Carlo Methods and Deep Neural Networks

Brent Harrison, Christopher Purdy, Mark O. Riedl

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

15 Scopus citations

Abstract

In this paper, we introduce an approach to automated story generation using Markov Chain Monte Carlo (MCMC) sampling. This approach uses a sampling algorithm based on Metropolis-Hastings to generate a probability distribution which can be used to generate stories via random sampling that adhere to criteria learned by recurrent neural networks. We show the applicability of our technique through a case study where we generate novel stories using an acceptance criteria learned from a set of movie plots taken from Wikipedia. This study shows that stories generated using this approach adhere to this criteria 85%-86% of the time.

Original language	English
Title of host publication	AAAI Workshop - Technical Report
Pages	191-197
Number of pages	7
Edition	2
ISBN (Electronic)	9781577357926
DOIs	https://doi.org/10.1609/aiide.v13i2.13003
State	Published - 2017
Event	13th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2017 - Snowbird, Little Cottonwood Canyon, United States Duration: Oct 5 2017 → Oct 9 2017

Publication series

Name	AAAI Workshop - Technical Report
Number	2
Volume	13

Conference

Conference	13th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2017
Country/Territory	United States
City	Snowbird, Little Cottonwood Canyon
Period	10/5/17 → 10/9/17

Bibliographical note

Publisher Copyright:
Copyright © 2017, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

ASJC Scopus subject areas

General Engineering
Artificial Intelligence
Computer Graphics and Computer-Aided Design
Computer Science Applications
Human-Computer Interaction
Software

Access to Document

10.1609/aiide.v13i2.13003

Cite this

@inproceedings{821003540a2d4edfb693bb7f239c0209,

title = "Toward Automated Story Generation with Markov Chain Monte Carlo Methods and Deep Neural Networks",

abstract = "In this paper, we introduce an approach to automated story generation using Markov Chain Monte Carlo (MCMC) sampling. This approach uses a sampling algorithm based on Metropolis-Hastings to generate a probability distribution which can be used to generate stories via random sampling that adhere to criteria learned by recurrent neural networks. We show the applicability of our technique through a case study where we generate novel stories using an acceptance criteria learned from a set of movie plots taken from Wikipedia. This study shows that stories generated using this approach adhere to this criteria 85%-86% of the time.",

author = "Brent Harrison and Christopher Purdy and Riedl, {Mark O.}",

note = "Publisher Copyright: Copyright {\textcopyright} 2017, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.; 13th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2017 ; Conference date: 05-10-2017 Through 09-10-2017",

year = "2017",

doi = "10.1609/aiide.v13i2.13003",

language = "English",

series = "AAAI Workshop - Technical Report",

number = "2",

pages = "191--197",

booktitle = "AAAI Workshop - Technical Report",

edition = "2",

}

Harrison, B, Purdy, C & Riedl, MO 2017, Toward Automated Story Generation with Markov Chain Monte Carlo Methods and Deep Neural Networks. in AAAI Workshop - Technical Report. 2 edn, AAAI Workshop - Technical Report, no. 2, vol. 13, pp. 191-197, 13th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2017, Snowbird, Little Cottonwood Canyon, United States, 10/5/17. https://doi.org/10.1609/aiide.v13i2.13003

TY - GEN

T1 - Toward Automated Story Generation with Markov Chain Monte Carlo Methods and Deep Neural Networks

AU - Harrison, Brent

AU - Purdy, Christopher

AU - Riedl, Mark O.

PY - 2017

Y1 - 2017

N2 - In this paper, we introduce an approach to automated story generation using Markov Chain Monte Carlo (MCMC) sampling. This approach uses a sampling algorithm based on Metropolis-Hastings to generate a probability distribution which can be used to generate stories via random sampling that adhere to criteria learned by recurrent neural networks. We show the applicability of our technique through a case study where we generate novel stories using an acceptance criteria learned from a set of movie plots taken from Wikipedia. This study shows that stories generated using this approach adhere to this criteria 85%-86% of the time.

AB - In this paper, we introduce an approach to automated story generation using Markov Chain Monte Carlo (MCMC) sampling. This approach uses a sampling algorithm based on Metropolis-Hastings to generate a probability distribution which can be used to generate stories via random sampling that adhere to criteria learned by recurrent neural networks. We show the applicability of our technique through a case study where we generate novel stories using an acceptance criteria learned from a set of movie plots taken from Wikipedia. This study shows that stories generated using this approach adhere to this criteria 85%-86% of the time.

UR - http://www.scopus.com/inward/record.url?scp=85165725341&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85165725341&partnerID=8YFLogxK

U2 - 10.1609/aiide.v13i2.13003

DO - 10.1609/aiide.v13i2.13003

M3 - Conference contribution

AN - SCOPUS:85165725341

T3 - AAAI Workshop - Technical Report

SP - 191

EP - 197

BT - AAAI Workshop - Technical Report

T2 - 13th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2017

Y2 - 5 October 2017 through 9 October 2017

ER -

Toward Automated Story Generation with Markov Chain Monte Carlo Methods and Deep Neural Networks

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this