research-article

Open access

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

Authors:

Judith van Stegeren,

Jakub MyśliwiecAuthors Info & Claims

FDG '21: Proceedings of the 16th International Conference on the Foundations of Digital Games

Article No.: 2, Pages 1 - 8

https://doi.org/10.1145/3472538.3472595

Published: 21 October 2021 Publication History

All formats PDF

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.

References

[1]

Prithviraj Ammanabrolu, William Broniec, Alex Mueller, Jeremy Paul, and Mark Riedl. 2019. Toward Automated Quest Generation in Text-Adventure Games. In Proceedings of the 4th Workshop on Computational Creativity in Language Generation. Association for Computational Linguistics, Tokyo, Japan, 1–12. https://www.aclweb.org/anthology/2019.ccnlg-1.1

[2]

Chris Bateman. 2007. Game writing: Narrative skills for videogames. Charles River Media.

[3]

Blizzard Entertainment. 2004. World of Warcraft. Game [PC]. Blizzard Entertainment, Irvine, California, US.

[4]

Margaret A. Boden. 2007. Creativity in a nutshell. Think 5, 15 (2007), 83–96. https://doi.org/10.1017/s147717560000230x

[5]

Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 1877–1901. https://proceedings.neurips.cc/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf

[6]

Bungie. 2014. Destiny. Game [PlayStation, Xbox]. Bungie, Bellevue, Washington, US.

[7]

CCP Games. 2003. EVE Online. Game [PC]. CCP Games, Reykjavík, Iceland.

[8]

Kate Compton, Quinn Kybartas, and Michael Mateas. 2015. Tracery: an author-focused generative text tool. In International Conference on Interactive Digital Storytelling. Springer, 154–161.

[9]

Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Association for Computational Linguistics, Minneapolis, Minnesota, 4171–4186. https://doi.org/10.18653/v1/N19-1423

[10]

Jonathon Doran and Ian Parberry. 2011. A Prototype Quest Generator Based on a Structural Analysis of Quests from Four MMORPGs. In Proceedings of the 2nd International Workshop on Procedural Content Generation in Games (Bordeaux, France) (PCGames ’11). Association for Computing Machinery, New York, NY, USA, Article 1, 8 pages. https://doi.org/10.1145/2000919.2000920

Digital Library

[11]

Jason Grinblat and C. Brian Bucklew. 2017. Subverting historical cause & effect: generation of mythic biographies in Caves of Qud. In Proceedings of the 12th International Conference on the Foundations of Digital Games (Hyannis, Massachusetts). ACM, ACM, New York, NY, USA, Article 76, 7 pages. https://doi.org/10.1145/3102071.3110574

Digital Library

[12]

Ari Holtzman, Jan Buys, Maxwell Forbes, Antoine Bosselut, David Golub, and Yejin Choi. 2018. Learning to Write with Cooperative Discriminators. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Melbourne, Australia, 1638–1649. https://www.aclweb.org/anthology/P18-1152

[13]

Chloé Kiddon, Luke Zettlemoyer, and Yejin Choi. 2016. Globally coherent text generation with neural checklist models. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. 329–339.

[14]

Tassilo Klein and Moin Nabi. 2019. Learning to Answer by Learning to Ask: Getting the Best of GPT-2 and BERT Worlds. arXiv preprint arXiv:1911.02365(2019).

[15]

Quinn Kybartas and Rafael Bidarra. 2017. A Survey on Story Generation Techniques for Authoring Computational Narratives. IEEE Transactions on Computational Intelligence and AI in Games 9, 3 (9 2017), 239–253. https://doi.org/10.1109/TCIAIG.2016.2546063

[16]

Quinn Kybartas and Clark Verbrugge. 2014. Analysis of ReGEN as a graph-rewriting system for quest generation. IEEE Transactions on Computational Intelligence and AI in Games 6, 2(2014), 228–242.

[17]

Jieh-Sheng Lee and Jieh Hsiang. 2020. PatentTransformer-2: Controlling Patent Text Generation by Structural Metadata. arXiv preprint arXiv:2001.03708(2020).

[18]

Jonathan Lessard, Etienne Brunelle-Leclerc, Timothy Gottschalk, Marc-Antoine Jetté-Léger, Odile Prouveur, and Christopher Tan. 2017. Striving for Author-Friendly Procedural Dialogue Generation. In Proceedings of the 12th International Conference on the Foundations of Digital Games (Hyannis, Massachusetts) (FDG ’17). Association for Computing Machinery, New York, NY, USA, Article 67, 6 pages. https://doi.org/10.1145/3102071.3116219

Digital Library

[19]

O.O. Marchenko, O.S. Radyvonenko, T.S. Ignatova, P.V. Titarchuk, and D.V. Zhelezniakov. 2020. Improving Text Generation Through Introducing Coherence Metrics. Cybernetics and Systems Analysis 56, 1 (2020), 13–21.

Digital Library

[20]

Curtis Onuczko, Duane Szafron, Jonathan Schaeffer, Maria Cutumisu, Jeff Siegel, Kevin Waugh, and Allan Schumacher. 2007. A Demonstration of SQUEGE: A CRPG Sub-Quest Generator. In Proceedings of the Third AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment(Stanford, California) (AIIDE’07). AAAI Press, 110–111.

[21]

Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. (2019). https://github.com/openai/gpt-2. Retrieved August 31, 2020.

[22]

James Ryan, Ethan Seither, Michael Mateas, and Noah Wardrip-Fruin. 2016. Expressionist: An authoring tool for in-game text generation. In International Conference on Interactive Digital Storytelling. Springer, 221–233.

Digital Library

[23]

James Owen Ryan, Casey Barackman, Nicholas Kontje, Taylor Owen-Milner, Marilyn A. Walker, Michael Mateas, and Noah Wardrip-Fruin. 2014. Combinatorial dialogue authoring. In International Conference on Interactive Digital Storytelling. Springer, 13–24.

[24]

Judith van Stegeren and Mariët Theune. 2019. Narrative Generation in the Wild: Methods from NaNoGenMo. In Proceedings of the Second Workshop on Storytelling. Association for Computational Linguistics, Florence, Italy, 65–74. https://www.aclweb.org/anthology/W19-3407

[25]

Judith van Stegeren and Mariët Theune. 2020. Fantastic Strings and Where to Find Them: The Quest for High-Quality Video Game Text Corpora. In Proceedings of the 2020 Workshop on Intelligent Narrative Technologies.

[26]

Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett(Eds.), Vol. 30. Curran Associates, Inc.https://proceedings.neurips.cc/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf

[27]

Marilyn A. Walker, Ricky Grant, Jennifer Sawyer, Grace I. Lin, Noah Wardrip-Fruin, and Michael Buell. 2011. Perceived or not perceived: Film character models for expressive NLG. In International Conference on Interactive Digital Storytelling. Springer, 109–121.

Digital Library

[28]

Nick Walton. 2019. AI Dungeon. Game [PC, Android, IOS]. https://www.aidungeon.io.

[29]

Lili Yao, Nanyun Peng, Weischedel Ralph, Kevin Knight, Dongyan Zhao, and Rui Yan. 2019. Plan-And-Write: Towards Better Automatic Storytelling. In Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19).

[30]

Rowan Zellers, Ari Holtzman, Hannah Rashkin, Yonatan Bisk, Ali Farhadi, Franziska Roesner, and Yejin Choi. 2019. Defending Against Neural Fake News. In Advances in Neural Information Processing Systems 32, H. Wallach, H. Larochelle, A. Beygelzimer, F. d’Alché Buc, E. Fox, and R. Garnett (Eds.). Curran Associates, Inc., 9054–9065. http://papers.nips.cc/paper/9106-defending-against-neural-fake-news.pdf

Cited By

Radwan AAmarneh MAlawneh HAshqar HMagableh AAlSobeh A(2024)Predictive Analytics in Mental Health Leveraging LLM Embeddings and Machine Learning Models for Social Media AnalysisInternational Journal of Web Services Research10.4018/IJWSR.33822221:1(1-22)Online publication date: 21-Feb-2024
https://dl.acm.org/doi/10.4018/IJWSR.338222
Yin MXiao R(2024)Press A or Wave: User Expectations for NPC Interactions and Nonverbal Behaviour in Virtual RealityProceedings of the ACM on Human-Computer Interaction10.1145/36770988:CHI PLAY(1-25)Online publication date: 15-Oct-2024
https://dl.acm.org/doi/10.1145/3677098
Lyman BEbrahimi ACox JChan SBarney CDe Schutter B(2024)Cardistry: Exploring a GPT Model Workflow as an Adapted Method of GaminiscingProceedings of the 19th International Conference on the Foundations of Digital Games10.1145/3649921.3656984(1-4)Online publication date: 21-May-2024
https://dl.acm.org/doi/10.1145/3649921.3656984
Show More Cited By

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

Recommendations

Personalized Quest and Dialogue Generation in Role-Playing Games: A Knowledge Graph- and Language Model-based Approach
CHI '23: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems

Procedural content generation (PCG) in video games offers unprecedented opportunities for customization and user engagement. Working within the specialized context of role-playing games (RPGs), we introduce a novel framework for quest and dialogue ...
Why MMORPG players do what they do: relating motivations to action categories

This paper presents an analysis of relations between player motivation and behaviour in a Massively Multiplayer Online Role-Playing Game (MMORPG). Player motivation is measured in terms of percentile ranks of motivational components for MMORPG players ...
A prototype quest generator based on a structural analysis of quests from four MMORPGs
PCGames '11: Proceedings of the 2nd International Workshop on Procedural Content Generation in Games

An analysis of over 750 quests from four popular RPGs (Eve Online, World of Warcraft, Everquest, and Vanguard: Saga of Heroes) reveals that RPG quests appear to share a common structure. We propose a classification of RPG quests based on this structure, ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

FDG '21: Proceedings of the 16th International Conference on the Foundations of Digital Games

August 2021

534 pages

ISBN:9781450384223

DOI:10.1145/3472538

Copyright © 2021 Owner/Author.

This work is licensed under a Creative Commons Attribution International 4.0 License.

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 21 October 2021

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Funding Sources

Nederlandse Organisatie voor Wetenschappelijk Onderzoek

Conference

FDG'21

FDG'21: The 16th International Conference on the Foundations of Digital Games 2021

August 3 - 6, 2021

QC, Montreal, Canada

Acceptance Rates

Overall Acceptance Rate 152 of 415 submissions, 37%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

26
Total Citations
View Citations
4,528
Total Downloads

Downloads (Last 12 months)1,286
Downloads (Last 6 weeks)147

Reflects downloads up to 12 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Radwan AAmarneh MAlawneh HAshqar HMagableh AAlSobeh A(2024)Predictive Analytics in Mental Health Leveraging LLM Embeddings and Machine Learning Models for Social Media AnalysisInternational Journal of Web Services Research10.4018/IJWSR.33822221:1(1-22)Online publication date: 21-Feb-2024
https://dl.acm.org/doi/10.4018/IJWSR.338222
Yin MXiao R(2024)Press A or Wave: User Expectations for NPC Interactions and Nonverbal Behaviour in Virtual RealityProceedings of the ACM on Human-Computer Interaction10.1145/36770988:CHI PLAY(1-25)Online publication date: 15-Oct-2024
https://dl.acm.org/doi/10.1145/3677098
Lyman BEbrahimi ACox JChan SBarney CDe Schutter B(2024)Cardistry: Exploring a GPT Model Workflow as an Adapted Method of GaminiscingProceedings of the 19th International Conference on the Foundations of Digital Games10.1145/3649921.3656984(1-4)Online publication date: 21-May-2024
https://dl.acm.org/doi/10.1145/3649921.3656984
Hong JLee YKim DChoi DYoon YLee GLee ZKim J(2024)A Context-Aware Onboarding Agent for Metaverse Powered by Large Language ModelsProceedings of the 2024 ACM Designing Interactive Systems Conference10.1145/3643834.3661579(1857-1874)Online publication date: 1-Jul-2024
https://dl.acm.org/doi/10.1145/3643834.3661579
Christiansen FHollensberg LJensen NJulsgaard KJespersen KNikolov I(2024)Exploring Presence in Interactions with LLM-Driven NPCs: A Comparative Study of Speech Recognition and Dialogue OptionsProceedings of the 30th ACM Symposium on Virtual Reality Software and Technology10.1145/3641825.3687716(1-11)Online publication date: 9-Oct-2024
https://dl.acm.org/doi/10.1145/3641825.3687716
Zhao YPan JDong YDong TWang GYing FShen QCao J(2024)Language Urban Odyssey: A Serious Game for Enhancing Second Language Acquisition through Large Language ModelsExtended Abstracts of the CHI Conference on Human Factors in Computing Systems10.1145/3613905.3651112(1-7)Online publication date: 11-May-2024
https://dl.acm.org/doi/10.1145/3613905.3651112
Giunchi DNuman NGatti ESteed A(2024)DreamCodeVR: Towards Democratizing Behavior Design in Virtual Reality with Speech-Driven Programming2024 IEEE Conference Virtual Reality and 3D User Interfaces (VR)10.1109/VR58804.2024.00078(579-589)Online publication date: 16-Mar-2024
https://doi.org/10.1109/VR58804.2024.00078
Värtinen SHämäläinen PGuckelsberger C(2024)Generating Role-Playing Game Quests With GPT Language ModelsIEEE Transactions on Games10.1109/TG.2022.322848016:1(127-139)Online publication date: Mar-2024
https://doi.org/10.1109/TG.2022.3228480
Yi Chan ESeow CWee Tan EWang MYau PCao Q(2024)SketchBoard: Sketch-Guided Storyboard Generation for Game Characters in the Game Industry2024 IEEE 22nd International Conference on Industrial Informatics (INDIN)10.1109/INDIN58382.2024.10774282(1-8)Online publication date: 18-Aug-2024
https://doi.org/10.1109/INDIN58382.2024.10774282
Turi LCavalini AComarela GOliveira-Santos TBadue CDe Souza A(2024)Analysis of Bias in GPT Language Models through Fine-tuning Containing Divergent Data2024 International Joint Conference on Neural Networks (IJCNN)10.1109/IJCNN60899.2024.10650574(1-8)Online publication date: 30-Jun-2024
https://doi.org/10.1109/IJCNN60899.2024.10650574
Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents