Abstract
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.- Anthology ID:
- 2023.nlp4convai-1.11
- Volume:
- Proceedings of the 5th Workshop on NLP for Conversational AI (NLP4ConvAI 2023)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Yun-Nung Chen, Abhinav Rastogi
- Venue:
- NLP4ConvAI
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 129–139
- Language:
- URL:
- https://aclanthology.org/2023.nlp4convai-1.11
- DOI:
- 10.18653/v1/2023.nlp4convai-1.11
- Cite (ACL):
- Gaetan Lopez Latouche, Laurence Marcotte, and Ben Swanson. 2023. Generating Video Game Scripts with Style. In Proceedings of the 5th Workshop on NLP for Conversational AI (NLP4ConvAI 2023), pages 129–139, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Generating Video Game Scripts with Style (Lopez Latouche et al., NLP4ConvAI 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2023.nlp4convai-1.11.pdf