Laurence Marcotte


2023

pdf
Generating Video Game Scripts with Style
Gaetan Lopez Latouche | Laurence Marcotte | Ben Swanson
Proceedings of the 5th Workshop on NLP for Conversational AI (NLP4ConvAI 2023)

While modern language models can generate a scripted scene in the format of a play, movie, or video game cutscene the quality of machine generated text remains behind that of human authors. In this work, we focus on one aspect of this quality gap; generating text in the style of an arbitrary and unseen character. We propose the Style Adaptive Semiparametric Scriptwriter (SASS) which leverages an adaptive weighted style memory to generate dialog lines in accordance with a character’s speaking patterns. Using the LIGHT dataset as well as a new corpus of scripts from twenty-three AAA video games, we show that SASS not only outperforms similar models but in some cases can also be used in conjunction with them to yield further improvement.