NLP for D&D
Principal Investigator: Nisansa de Silva
This project attempts to generate adventures, images, and encounters for Dungeons and Dragons, the world's most popular Table Top Role Playing Game.
One part of this project is to create a system capable of generating stand-alone adventure modules. This refers to a playable scenario for the players that can be used by a Dungeon Master (Game Master). The module will have a concise and cohesive narrative while employing gaming strategies and narrative elements found in a typical adventure module.
Objectives:
- Generating coherent and consistent Dungeons and Dragons adventure modules.
- Generating coherent and consistent images for a given text document in the context of D&D domain.
- Generating cohesive D&D Encounters with monsters and situations that align with D&D lore.
Keywords: Natural Language Processing | Machine Learning / Deep Learning | DnD |
Publications
Conference Papers
Gayashan Weerasundara and Nisansa de Silva, "A Multi-Stage Approach to Image Consistency in Zero-Shot Character Art Generation for the D\&D Domain", in Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART, SciTePress, 2024, pp. 235-242. doi: 10.5220/0012317600003636
Gayashan Weerasundara and Nisansa de Silva, "Comparative Analysis of Named Entity Recognition in the Dungeons and Dragons Domain", in Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing, 2023, pp. 1225--1233.
Aravinth Sivaganeshan and Nisansa De Silva, "Fine Tuning Named Entity Extraction Models for the Fantasy Domain", in 2023 Moratuwa Engineering Research Conference (MERCon), 2023, pp. 346--351. doi: 10.1109/MERCon60487.2023.10355501
Akila Peiris and Nisansa de Silva, "SHADE: Semantic Hypernym Annotator for Domain-Specific Entities-Dungeons and Dragons Domain Use Case", in 2023 IEEE 17th International Conference on Industrial and Information Systems (ICIIS), 2023, pp. 1--6. doi: 10.1109/ICIIS58898.2023.10253606
Akila Peiris and Nisansa de Silva, "Synthesis and Evaluation of a Domain-specific Large Data Set for Dungeons \& Dragons", in Proceedings of the 36th Pacific Asia Conference on Language, Information and Computation, 2022, pp. 415--424.
Team
Faculty
MSc Students
Alumni-MSc Students
Grants
