Automating Direct Speech Variations in Stories and Games
This addresses the tedious and time-consuming task of manually authoring dialogue variations for characters in large games, though it appears incremental as it builds on an existing translation tool.
The paper tackled the problem of automating dialogue authoring for games by enabling direct speech modeling in a narrative representation, allowing character substitution in dialogues. They implemented and evaluated this for generating dialogue in dynamic open-world games, conducting a pilot study on human perceptions of character personalities.
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.