QuestVille: Procedural Quest Generation Using NLP Models

Suzan Al-Nassar; Anthonie Schaap; Michael Van Der Zwart; Mike Preuss; Marcello A. Gómez-Maureira

doi:10.1145/3582437.3587188

QuestVille: Procedural Quest Generation Using NLP Models

Suzan Al-Nassar
, Anthonie Schaap
, Michael Van Der Zwart
, Mike Preuss
, Marcello A. Gómez-Maureira

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

16 Citations (Scopus)

355 Downloads (Pure)

Abstract

Developers face a time-consuming task when creating quests in video games. To ease this burden, Procedural Content Generation (PCG) techniques can be used to automatically generate quests. While PCG has been applied to various areas of game development, it can be difficult to create meaningful narratives for quests. This paper presents a new method for generating engaging quests by combining PCG with Natural Language Processing (NLP) using the models BERT and GPT-2 in a case study game called QuestVille. The paper details the implementation of these models and the challenges encountered. The results suggest that the use of BERT and GPT-2 has potential for creating compelling narrative content. Advancements in AI research may improve on the limitations discussed.

Original language	English
Title of host publication	FDG '23
Subtitle of host publication	Proceedings of the 18th International Conference on the Foundations of Digital Games, FDG 2023
Editors	Phil Lopes, Filipe Luz, Antonios Liapis, Henrik Engstrom
Place of Publication	New York, NY
Publisher	Association for Computing Machinery
ISBN (Electronic)	978-1-4503-9855-8
ISBN (Print)	978-1-4503-9856-5
DOIs	https://doi.org/10.1145/3582437.3587188
Publication status	Published - 12 Apr 2023
Event	18th International Conference on the Foundations of Digital Games, FDG 2023 - Lisbon, Portugal Duration: 11 Apr 2023 → 14 Apr 2023 Conference number: 18

Conference

Conference	18th International Conference on the Foundations of Digital Games, FDG 2023
Abbreviated title	FDG 2023
Country/Territory	Portugal
City	Lisbon
Period	11/04/23 → 14/04/23

Keywords

Game AI
Procedural content generation
Procedural quests

Access to Document

10.1145/3582437.3587188Licence: CC BY

ArticleFinal published version, 556 KBLicence: CC BY

Cite this

Al-Nassar, S., Schaap, A., Zwart, M. V. D., Preuss, M., & Gómez-Maureira, M. A. (2023). QuestVille: Procedural Quest Generation Using NLP Models. In P. Lopes, F. Luz, A. Liapis, & H. Engstrom (Eds.), FDG '23: Proceedings of the 18th International Conference on the Foundations of Digital Games, FDG 2023 Article 50 Association for Computing Machinery. https://doi.org/10.1145/3582437.3587188

@inproceedings{baae5c9c907d491fbea0091da1b2cbc5,

title = "QuestVille: Procedural Quest Generation Using NLP Models",

abstract = "Developers face a time-consuming task when creating quests in video games. To ease this burden, Procedural Content Generation (PCG) techniques can be used to automatically generate quests. While PCG has been applied to various areas of game development, it can be difficult to create meaningful narratives for quests. This paper presents a new method for generating engaging quests by combining PCG with Natural Language Processing (NLP) using the models BERT and GPT-2 in a case study game called QuestVille. The paper details the implementation of these models and the challenges encountered. The results suggest that the use of BERT and GPT-2 has potential for creating compelling narrative content. Advancements in AI research may improve on the limitations discussed.",

keywords = "Game AI, Procedural content generation, Procedural quests",

author = "Suzan Al-Nassar and Anthonie Schaap and Zwart, \{Michael Van Der\} and Mike Preuss and G{\'o}mez-Maureira, \{Marcello A.\}",

note = "Publisher Copyright: {\textcopyright} 2023 Owner/Author.; 18th International Conference on the Foundations of Digital Games, FDG 2023, FDG 2023 ; Conference date: 11-04-2023 Through 14-04-2023",

year = "2023",

month = apr,

day = "12",

doi = "10.1145/3582437.3587188",

language = "English",

isbn = "978-1-4503-9856-5",

editor = "Phil Lopes and Filipe Luz and Antonios Liapis and Henrik Engstrom",

booktitle = "FDG '23",

publisher = "Association for Computing Machinery",

address = "United States",

}

Al-Nassar, S, Schaap, A, Zwart, MVD, Preuss, M & Gómez-Maureira, MA 2023, QuestVille: Procedural Quest Generation Using NLP Models. in P Lopes, F Luz, A Liapis & H Engstrom (eds), FDG '23: Proceedings of the 18th International Conference on the Foundations of Digital Games, FDG 2023., 50, Association for Computing Machinery, New York, NY, 18th International Conference on the Foundations of Digital Games, FDG 2023, Lisbon, Portugal, 11/04/23. https://doi.org/10.1145/3582437.3587188

QuestVille: Procedural Quest Generation Using NLP Models. / Al-Nassar, Suzan; Schaap, Anthonie; Zwart, Michael Van Der et al.
FDG '23: Proceedings of the 18th International Conference on the Foundations of Digital Games, FDG 2023. ed. / Phil Lopes; Filipe Luz; Antonios Liapis; Henrik Engstrom. New York, NY: Association for Computing Machinery, 2023. 50.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - QuestVille

T2 - 18th International Conference on the Foundations of Digital Games, FDG 2023

AU - Al-Nassar, Suzan

AU - Schaap, Anthonie

AU - Zwart, Michael Van Der

AU - Preuss, Mike

AU - Gómez-Maureira, Marcello A.

N1 - Conference code: 18

PY - 2023/4/12

Y1 - 2023/4/12

N2 - Developers face a time-consuming task when creating quests in video games. To ease this burden, Procedural Content Generation (PCG) techniques can be used to automatically generate quests. While PCG has been applied to various areas of game development, it can be difficult to create meaningful narratives for quests. This paper presents a new method for generating engaging quests by combining PCG with Natural Language Processing (NLP) using the models BERT and GPT-2 in a case study game called QuestVille. The paper details the implementation of these models and the challenges encountered. The results suggest that the use of BERT and GPT-2 has potential for creating compelling narrative content. Advancements in AI research may improve on the limitations discussed.

AB - Developers face a time-consuming task when creating quests in video games. To ease this burden, Procedural Content Generation (PCG) techniques can be used to automatically generate quests. While PCG has been applied to various areas of game development, it can be difficult to create meaningful narratives for quests. This paper presents a new method for generating engaging quests by combining PCG with Natural Language Processing (NLP) using the models BERT and GPT-2 in a case study game called QuestVille. The paper details the implementation of these models and the challenges encountered. The results suggest that the use of BERT and GPT-2 has potential for creating compelling narrative content. Advancements in AI research may improve on the limitations discussed.

KW - Game AI

KW - Procedural content generation

KW - Procedural quests

UR - https://www.scopus.com/pages/publications/85153576488

U2 - 10.1145/3582437.3587188

DO - 10.1145/3582437.3587188

M3 - Conference contribution

SN - 978-1-4503-9856-5

BT - FDG '23

A2 - Lopes, Phil

A2 - Luz, Filipe

A2 - Liapis, Antonios

A2 - Engstrom, Henrik

PB - Association for Computing Machinery

CY - New York, NY

Y2 - 11 April 2023 through 14 April 2023

ER -

QuestVille: Procedural Quest Generation Using NLP Models

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this