# Event Representations for Automated Story Generation with Deep Neural Nets

## TL;DR

This paper explores event representations for automated story generation using deep neural networks, focusing on intermediate abstractions to improve coherence and semantic retention in generated stories.

## Contribution

It introduces a novel preprocessing technique for converting stories into event sequences and compares different event representations for better story generation.

## Key findings

- Event representations impact the coherence of generated stories.
- Decomposition into event2event and event2sentence improves story generation.
- Empirical results show certain representations better preserve story semantics.

## 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.