Fine-tuning GPT-2 on annotated RPG quests for NPC dialogue generation

Judith van Stegeren, Jakub Myśliwiec

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

2 Downloads (Pure)

Abstract

GPT-2, a neural language model trained on a large dataset of English web text, has been used in a variety of natural language generation tasks because of the language quality and coherence of its outputs. In order to investigate the usability of GPT-2 for text generation for video games, we fine-tuned GPT-2 on a corpus of video game quests and used this model to generate dialogue lines for quest-giver NPCs in a role-playing game. We show that the model learned the structure of quests and NPC dialogue, and investigate how the temperature parameter influences the language quality and creativity of the output artifacts. We evaluated our approach with a crowdsource experiment in which human judges were asked to rate hand-written and generated quest texts on language quality, coherence and creativity.
Original languageEnglish
Title of host publicationFDG'21: The 16th International Conference on the Foundations of Digital Games (FDG) 2021
EditorsAllan Fowler, Johanna Pirker, Alesandro Alessandro Canossa, Ali Ali Arya, Casper Harteveld
Place of PublicationMontreal, QC, Canada
PublisherAssociation for Computing Machinery (ACM)
Pages1
Number of pages8
ISBN (Electronic)9781450384223
DOIs
Publication statusPublished - 3 Aug 2021
Event16th International Conference on the Foundations of Digital Games, FDG 2021 - Online Conference
Duration: 2 Aug 20216 Aug 2021
Conference number: 16
http://fdg2021.org/

Conference

Conference16th International Conference on the Foundations of Digital Games, FDG 2021
Abbreviated titleFDG 2021
CityOnline Conference
Period2/08/216/08/21
Internet address

Keywords

  • GPT-2
  • Transformers
  • World of Warcraft
  • English
  • NPC dialogue
  • Natural language generation
  • procedural content generation for games
  • quest generation
  • MMORPG

Fingerprint

Dive into the research topics of 'Fine-tuning GPT-2 on annotated RPG quests for NPC dialogue generation'. Together they form a unique fingerprint.

Cite this