Comparative Analysis of Named Entity Recognition in the Dungeons and Dragons Domain

Sep 29, 2026

Many NLP tasks work well for general English but degrade in specialized domains such as fantasy literature. Named Entity Recognition (NER), which detects and categorizes entities, is particularly affected by invented names, variant spellings, and ambiguity. This study evaluates 10 open-source NER models on 7 Dungeons and Dragons adventure books by annotating named entities and measuring precision. Results show Flair, Trankit, and SpaCy outperform others without domain-specific modification.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages9

Reading Time23 min

AccessFree to download

Introduction

Related Works

Data Collection and Annotation

Methods and Findings

Insights and Conclusion

Future Work

Comparative Analysis of Named Entity Recognition in the Dungeons and Dragons Domain Gayashan Weerasundara and Nisansa de Silva Department of Computer Science & Engineering University of Moratuwa, Sri Lanka {gayashan.22, [NisansaDdS](NisansaDdS}@cse.mrt.ac.lk)[}](NisansaDdS}@cse.mrt.ac.lk)[@cse.mrt.ac.lk](NisansaDdS}@cse.mrt.ac.lk) Abstract Many NLP tasks, although well-resolved for general English, face challenges in specific domains like fantasy literature. This is evident in Named Entity Recognition (NER), which detects and categorizes entities in text. We analyzed 10 NER models on 7 Dungeons and Dragons (D&D) adventure books to assess domainspecific performance. Using open-source Large Language Models, we annotated named entities in these books and evaluated each model’s precision. Our findings indicate that, without modifications, Flair, Trankit, and Spacy outperform others in identifying named entities in the D&D context. 1 Introduction Named Entity Recognition (NER) targets the identification and classification of textual entities, such as names and locations. In the diverse and intricate vocabulary of fantasy literature, like that of Dungeons and Dragons (D&D), NER becomes challenging (Zagal and Deterding, 2018) . D&D, a prominent fantasy literature domain, spans content for its namesake tabletop game (Peiris and de Silva, 2022, 2023 ; Zhou et al., 2022) . These narratives inhabit fictional realms like Forgotten Realms and Dragonlance, bursting with characters, locations, and objects (Gygax and Arneson, 1974) . NER’s utility in fantasy literature is vast: from extracting information and summarizing text to character analysis and plot creation. However, conventional NER models, primarily trained on standard datasets like CoNLL-2003 (Tjong Kim Sang and De Meulder, 2003) or OntoNotes 5.0 (Weischedel et al., 2013), might falter on fantasy texts due to their unique linguistic attributes. Recognizing the need for domain-specific adaptation, other specialized areas such as law (Sugathadasa et al., 2017), medicine (de Silva et al., 2017), and the dynamic landscape of social media (de Silva and Dou, 2021) have already seen research emphasizing it. Large models, as Yao et al. (2021) points out, can face domain adaptation challenges, stressing the need for evaluating NER models specifically on fantasy content. Fantasy NER has potential, especially with advancements in image generation. A notable application might involve an image generation model leveraging NER tags to derive prompts and subsequently produce contextually relevant images. Our study contrasts 10 NER models across seven D&D books, each averaging 118,000 words. Manual annotations of entities were made and juxtaposed against model outputs. Through precision assessments and named entity distribution analyses, we glean insights into model performances in the fantasy domain. Our key contributions include: • A pioneering, comprehensive NER model evaluation on fantasy content. • An annotated D&D book dataset for NER studies. • A deep dive into varied NER models’strengths and pitfalls in the fantasy realm. • Discussions on NER’s role and prospects in fantasy literature. Following this, Section 2 delves into related NER and fantasy literature works. Section 3 details our data and annotation process, while Section 4 unveils our methods and findings. Sections 5 and 6 respectively discuss insights and conclude our research, and Section 7 outlines potential future endeavors. 2 Related Works NER has seen the development of various models like rule-based systems, statistical models, neural 1225 Proceedings of Recent Advances in Natural Language Processing, pages 1225–1233 Varna, Sep 4–6, 2023 [https://doi.org/10.26615/978-954-452-092-2_130](https://doi.org/10.26615/978-954-452-092-2_130) networks, and transformer-based models (Seo et al., 2021 ; Liu et al., 2022 ; Krasnov et al., 2021) . Although they’ve been trained on standard datasets, t

FAQs

Why is NER challenging in the Dungeons and Dragons domain?

NER becomes difficult in fantasy literature due to invented names, variable spellings, entity ambiguity, and the limited availability of domain-specific resources.

How is the study conducted to compare NER models?

The study annotates named entities in seven Dungeons and Dragons books using open-source large language models, then evaluates 10 NER models by measuring precision and analyzing entity distributions.

Which NER models perform best for the D&D context?

Without modifications, Flair, Trankit, and SpaCy are reported as outperforming the other models in identifying named entities in the D&D setting.

Sep 29, 2026

Upload by supergirl