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

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.

[1]  Martha Palmer,et al.  Verbnet: a broad-coverage, comprehensive verb lexicon , 2005 .

[2]  Rafael Pérez y Pérez,et al.  MEXICA: A computer model of a cognitive account of creative writing , 2001, J. Exp. Theor. Artif. Intell..

[3]  Mark O. Riedl,et al.  Event Representations for Automated Story Generation with Deep Neural Nets , 2017, AAAI.

[4]  Stephen G. Ware,et al.  Fast and Diverse Narrative Planning through Novelty Pruning , 2016, AIIDE.

[5]  Julian Togelius,et al.  DeepTingle , 2017, ICCC.

[6]  Boyang Li,et al.  Story Generation with Crowdsourced Plot Graphs , 2013, AAAI.

[7]  S. Chib,et al.  Understanding the Metropolis-Hastings Algorithm , 1995 .

[8]  Mihai Surdeanu,et al.  The Stanford CoreNLP Natural Language Processing Toolkit , 2014, ACL.

[9]  Melissa Roemmele,et al.  Writing Stories with Help from Recurrent Neural Networks , 2016, AAAI.

[10]  Boyang Li,et al.  An Offline Planning Approach to Game Plotline Adaptation , 2010, AIIDE.

[11]  Francisco Gomes de Matos,et al.  How we write. Writing as creative design , 1999 .

[12]  Stephen John Turner,et al.  The Creative Process: A Computer Model of Storytelling and Creativity , 1994 .

[13]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[14]  Marc Cavazza,et al.  Planning characters' behaviour in interactive storytelling , 2002, Comput. Animat. Virtual Worlds.

[15]  Marc Cavazza,et al.  Generative Story Worlds as Linear Logic Programs , 2014 .

[16]  Raquel Hervás,et al.  Story plot generation based on CBR , 2004, Knowl. Based Syst..

[17]  Natlie Dehn,et al.  Story Generation After TALE-SPIN , 1981, IJCAI.

[18]  Robert Michael Young,et al.  Narrative Planning: Balancing Plot and Character , 2010, J. Artif. Intell. Res..

[19]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[20]  James R. Meehan,et al.  TALE-SPIN, An Interactive Program that Writes Stories , 1977, IJCAI.

[21]  Reid Swanson,et al.  Say Anything: Using Textual Case-Based Reasoning to Enable Open-Domain Interactive Storytelling , 2012, TIIS.

[22]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[23]  Marc Cavazza,et al.  Controlling Narrative Generation with Planning Trajectories: The Role of Constraints , 2009, ICIDS.

[24]  Xinlei Chen,et al.  Learning Visual Storylines with Skipping Recurrent Neural Networks , 2016, ECCV.