Toward Automated Story Generation with Markov Chain Monte Carlo Methods and Deep Neural Networks
By Brent Harrison, Chris Purdy, Mark O. Riedl. 2021
39 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Natural Language Processing, Generative Models
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Jianfeng Gao
- Yejin Choi
- Mohit Bansal
- Graham Neubig
- Noah A. Smith
- Luke S. Zettlemoyer
- Jason Aaron Edward Weston
- Yoav Goldberg
In Natural Language Processing
- Jianfeng Gao
- Yejin Choi
- Mohit Bansal
- Jason Aaron Edward Weston
- Graham Neubig
- Luke S. Zettlemoyer
- Noah A. Smith
- Michael Lewis
In Generative Models
- Angela Fan
- Yoav Goldberg
- Eyal Orbach
- Michael Lewis
- Michel Galley
- Chris Quirk
- Yann Dauphin
- Yejin Choi
Citations in the corpus
- Hierarchical Neural Story Generation (2018, methodology): “Similarly, Harrison et al. (2017) generate summaries of movies as sequences of events using an RNN, then sample event representations using MCMC.”
- Facts2Story: Controlling Text Generation by Key Facts (2020, background): “Earlier attempts at harnessing neural techniques for story generation struggled with staying coherent for long periods of time, and proposed solutions in the form of two-stage processes which first generate skeletal structures and then expand them into longer texts (Harrison et al., 2017; Martin et ”
- CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling (2018, background): “Harrison, Purdy, and Riedl (2017) utilize MH to sample an event sequence in the task of story generation, which cannot be directly used for sentence generation.”
- Text Editing by Command (2020, background): “, 2018), events (Martin et al., 2017; Harrison et al., 2017), plot words or word skeletons (Xu et al.”
- Generating Fluent Adversarial Examples for Natural Languages (2019, background): “, 2018), guided open story generation (Harrison et al., 2017), etc.”