dAIrector: Automatic Story Beat Generation through Knowledge Synthesis

TL;DR

dAIrector is an AI system that collaborates with human storytellers to generate narrative arcs and plot ideas, enhancing improvisational storytelling through automated knowledge synthesis.

Contribution

This work introduces dAIrector, a novel system architecture for automated story beat generation, including evaluation metrics and open-source code for community use.

Findings

Quantitative evaluation of design choices

Qualitative feedback from a professional improviser

Open-source implementation for testing and development

Abstract

dAIrector is an automated director which collaborates with humans storytellers for live improvisational performances and writing assistance. dAIrector can be used to create short narrative arcs through contextual plot generation. In this work, we present the system architecture, a quantitative evaluation of design choices, and a case-study usage of the system which provides qualitative feedback from a professional improvisational performer. We present relevant metrics for the understudied domain of human-machine creative generation, specifically long-form narrative creation. We include, alongside publication, open-source code so that others may test, evaluate, and run the dAIrector.