Step: A Highly Expressive Text Generation Language

Abstract

Games often generate text from human-authored templates and adapt that text to relevant context. Many systems have been developed to aid this process using tech-niques such as context-free grammars, randomization, logic programming, global state, and HTN planning. In this paper, I present Step, a novel programming language for text generation. So far as I can determine, previous techniques can all be implemented within Step using a few lines of code. This allows designers to mix-and-match features as needed, without having to write an interpreter for a new language. While extremely expressive as a programming language, Step is also intended to allow writers to add new text to an existing system with minimal markup and little knowledge of programming. In a head-to-head comparison, the Step implementation was more compact than, and used less markup than, a Prolog implementation of the same generator.