[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-512927-105":59,"doc-detail-512927-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","synthesis-and-evaluation-of-a-domain-specific-large-data-set-for-dungeons-dragons","Synthesis and Evaluation of a Domain-specific Large Data Set for Dungeons & Dragons","","This paper introduces the Forgotten Realms Wiki (FRW) dataset and domain-specific natural language generation using FRW, alongside related analyses. Forgotten Realms, the default setting for Dungeons & Dragons, is mined from the Forgotten Realms Fandom wiki containing over 45,200 articles. The dataset includes 11 sub-datasets in multiple representations, enabling similarity benchmarking and named entity classification evaluation grounded in Forgotten Realms lore.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/synthesis-and-evaluation-of-a-domain-specific-large-data-set-for-dungeons-dragons/512927/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/synthesis-and-evaluation-of-a-domain-specific-large-data-set-for-dungeons-dragons/512927.png","ImageObject",300,407,{"name":92,"@type":93},"Stanford","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-06","2026-10-06",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",12,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What dataset does the paper introduce for the Dungeons & Dragons domain?","Question",{"text":113,"@type":114},"It introduces the Forgotten Realms Wiki (FRW) dataset extracted from the Forgotten Realms Fandom wiki, containing over 45,200 articles.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How is the FRW dataset structured and represented?",{"text":118,"@type":114},"The FRW dataset is built as 11 sub-datasets across multiple formats, including raw and title-annotated plain text, directed link graphs, wiki infoboxes, Poincaré embeddings, and Word2Vec/Doc2Vec models.",{"name":120,"@type":111,"acceptedAnswer":121},"What evaluations and tasks are performed using the corpus?",{"text":122,"@type":114},"The work presents a pairwise similarity comparison benchmark using similarity measures, performs D&D domain-specific natural language generation, and evaluates named entity classification with respect to Forgotten Realms lore.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},512927,1791377260,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":145,"read_time":146,"preview_page_count":19,"preview_urls":147},2336477552062,"https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d","Synthesis and Evaluation of a Domain-speciﬁc Large Data Set for  \nDungeons & Dragons  \nAkila Peiris and Nisansa de Silva Department of Computer Science & Engineering, University of Moratuwa, Sri Lanka {akila.21,[nisansadds}@cse.mrt.ac.lk](nisansadds}@cse.mrt.ac.lk)  \narXiv :2212 .09080v1 [ cs .CL] 18 Dec 2022  \nAbstract  \nThis paper introduces the Forgotten Realms Wiki (FRW) data set and domain speciﬁc natural language generation using FRW along with related analyses. Forgotten Realms is the defacto default setting of the popular open ended tabletop fantasy role playing game, Dungeons & Dragons. The data set was extracted from the Forgotten Realms Fandom wiki consisting of more than over 45,200 articles. The FRW data set is constituted of 11 sub-data sets in a number of formats: raw plain text, plain text annotated by article title, directed link graphs, wiki info-boxes annotated by the wiki article title, Poincaré embedding of ﬁrst link graph, multiple Word2Vec and Doc2Vec models of the corpus. This is the ﬁrst data set of this size for the Dungeons & Dragons domain. We then present a pairwise similarity comparison benchmark which utilizes similarity measures.  \nIn addition, we 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.  \n1 Introduction  \nSpecialized and domain speciﬁc data sets are useful for a number of advanced tasks in the domain of Natural Language Processing (NLP) . For example, recent studies have shown that the domain speciﬁcity signiﬁcantly impacts vital NLP tasks such as measuring semantic similarity (Sugathadasa et al., 2017) and domain speciﬁc text generation (Lebret et al., 2016) . Further, it has been shown that models developed using data from a generic domain do not seamlessly transfer to tasks in a speciﬁc domain (Rajapaksha et al., 2020) . Fantasy domains could be considered an extreme case of domainspeciﬁc data, as it is possible to observe the full spectrum of deviations from the non-domain speciﬁc (general domain) usage, both in the lexical and semantic perspectives. An example for lexical differences is the usage of dwarves as the plural  \nform of dwarf in the fantasy genre 1 in place of the general domain spelling dwarfs. An example for semantic differences can be seen in the words Ghost2 and Wraith3. In the Merriam-Webster dictionary, they are given as synonyms in the generic domain4 while in the domain of the fantasy roleplaying game Dungeons & Dragons, they are deﬁned as two distinct creatures. In this paper, we present the FRW data set, speciﬁc to the Forgotten Realms setting of Dungeons & Dragons. We expect our data set to be useful for in-domain tasks such as text generation (Zhang et al., 2019), information extraction (de Silva and Dou, 2021), and information retrieval (Sugathadasa et al., 2018) . We also anticipate our data set being vital for cross domain tasks such as text alignment (Sanchez-Perez et al., 2014), style transfer (Fu et al., 2018), and summarizing (El-Kassas et al., 2020) . As a primer for these usages, we introduce a pairwise similarity comparison benchmark and evaluate the domainspeciﬁc free text generation task.  \n1.1 Dungeons & Dragons  \nDungeons & Dragons (D&D or DnD), is an openended pen and paper tabletop role playing game (RPG) which has been commercially available since Gygax and Arneson (1974) published the ﬁrst version. The games are primarily based on fantasy genre. However, there is a plethora of other settings ranging from science ﬁction, post-apocalyptic to hollow world and much more. Even within a selected genre, it is highly customizable, for example, a fantasy setting might be in high or low fantasy. D&D has a predeﬁned set of rules governing almost every aspect of the gameplay including the setting. A setting has a lore, species and artifacts  \n1This is inherited from the spelling used in the Lord of the Rings and other relevant publications by","cbCaifLCkLQ94l8t","https://ap.wps.com/l/cbCaifLCkLQ94l8t","pdf",2128075,13,"English","# Abstract\n# 1 Introduction\n## 1.1 Dungeons & Dragons\n## 1.2 Forgotten Realms Wiki","[{\"question\":\"What dataset does the paper introduce for the Dungeons \\u0026 Dragons domain?\",\"answer\":\"It introduces the Forgotten Realms Wiki (FRW) dataset extracted from the Forgotten Realms Fandom wiki, containing over 45,200 articles.\"},{\"question\":\"How is the FRW dataset structured and represented?\",\"answer\":\"The FRW dataset is built as 11 sub-datasets across multiple formats, including raw and title-annotated plain text, directed link graphs, wiki infoboxes, Poincaré embeddings, and Word2Vec/Doc2Vec models.\"},{\"question\":\"What evaluations and tasks are performed using the corpus?\",\"answer\":\"The work presents a pairwise similarity comparison benchmark using similarity measures, performs D\\u0026D domain-specific natural language generation, and evaluates named entity classification with respect to Forgotten Realms lore.\"}]","Synthesis and Evaluation of a Domain-specific Large Data Set for Dungeons & Dragons | PDF",1791277854,33,[148,152,156,160],{"page_no":8,"url":149,"width":150,"height":151},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/d27dbd1ccbab9f61ce128f27e3640c77.webp",983,1390,{"page_no":14,"url":153,"width":154,"height":155},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/5d344ac84d4ff039c93c21613cee43e8.webp",982,1388,{"page_no":81,"url":157,"width":158,"height":159},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/ed0ea44e4b6481c920bb237dc5362da1.webp",981,1387,{"page_no":19,"url":161,"width":162,"height":163},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/796301bdbd22511f194bebe8fbce1164.webp",980,1385]