Automating Direct Speech Variations in Stories and Games

TL;DR

This paper presents a method to automate the generation of character-specific direct speech in stories and games, enhancing dialogue realism and reducing manual effort through a narrative representation and natural language generation.

Contribution

It introduces an expanded translation tool that models direct speech in a narrative framework, enabling character substitution and dynamic dialogue generation for large, open-world games.

Findings

Successful implementation of character substitution in dialogues

Potential for generating dynamic dialogues in open-world games

Positive pilot study on human perception of character personalities

Abstract

Dialogue authoring in large games requires not only content creation but the subtlety of its delivery, which can vary from character to character. Manually authoring this dialogue can be tedious, time-consuming, or even altogether infeasible. This paper utilizes a rich narrative representation for modeling dialogue and an expressive natural language generation engine for realizing it, and expands upon a translation tool that bridges the two. We add functionality to the translator to allow direct speech to be modeled by the narrative representation, whereas the original translator supports only narratives told by a third person narrator. We show that we can perform character substitution in dialogues. We implement and evaluate a potential application to dialogue implementation: generating dialogue for games with big, dynamic, or procedurally-generated open worlds. We present a pilot study on human perceptions of the personalities of characters using direct speech, assuming unknown personality types at the time of authoring.