Event Representations for Automated Story Generation with Deep Neural Nets
This addresses the challenge of automated story generation for applications in creative writing or entertainment, but it is incremental as it builds on existing neural network methods with a new representation approach.
The paper tackles the problem of generating coherent stories by proposing event representations as a mid-level abstraction between words and sentences, and shows empirical results comparing different event representations for event successor generation and translation to natural language.
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.