NLP for D&D
ActivePI: 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.
@inproceedings{peiris2022primer,
title={{A Primer on Synthesis and Evaluation of a Domain-specific Large Data Set for Dungeons \& Dragons}},
author={Peiris, Akila and de Silva, Nisansa},
booktitle={6th Widening NLP Workshop},
year={2022},
abstract={This paper introduces the Forgotten Realms Wiki (FRW) data set and uses it for domain specific natural language generation. The data set was extracted from Wikipedia-esque website Forgotten Realms Fandom wiki, dedicated to the tabletop role playing game Dungeons and Dragons (D\&D). The FRW data set is constituted of 11 sub-data sets in varying formats intended for different NLP tasks including text generation and semantic similarity comparison. This is the first data set of this size for the D\&D domain. We then present a pairwise similarity comparison benchmark and perform D\&D domain specific natural language generation using the corpus and evaluate the named entity classification with respect to the lore of Forgotten Realms.},
misc={https://scholar.google.com/citations?view_op=view_citation&hl=en&user=m41AMuMAAAAJ&citation_for_view=m41AMuMAAAAJ:9yKSN-GCB0IC,NLP:ML:DND,https://goo.gl/iY6aTr}
}