Event representations for automated story generation with deep neural nets

Thumbnail Image

Links to Files

https://dl.acm.org/doi/10.5555/3504035.3504141

Permanent Link

http://hdl.handle.net/11603/37742

Collections

UMBC Computer Science and Electrical Engineering Department

Author/Creator

Author/Creator ORCID

https://orcid.org/0000-0002-0623-599X

Date

2018-02-02

Type of Work

conference papers and proceedings
Text

Department

Program

Citation of Original Publication

Martin, Lara J., Prithviraj Ammanabrolu, Xinyu Wang, William Hancock, Shruti Singh, Brent Harrison, and Mark O. Riedl. "Event Representations for Automated Story Generation with Deep Neural Nets". Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence and Thirtieth Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence, AAAI’18/IAAI’18/EAAI’18, 2 February 2018, 868–75. https://dl.acm.org/doi/10.5555/3504035.3504141

Rights

This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.

Subjects

neural nets
language models

Abstract

Automated story generation is the problem of automatically selecting a sequence of events, actions, or words that can be told as a story. We seek to develop a system that can generate stories by learning everything it needs to know from textual story corpora. To date, recurrent neural networks that learn language models at character, word, or sentence levels have had little success generating coherent stories. We explore the question of event representations that provide a mid-level of abstraction between words and sentences in order to retain the semantic information of the original data while minimizing event sparsity. We present a technique for preprocessing textual story data into event sequences. We then present a technique for automated story generation whereby we decompose the problem into the generation of successive events (event2event) and the generation of natural language sentences from events (event2sentence). We give empirical results comparing different event representations and their effects on event successor generation and the translation of events to natural language.