[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-140664-105":59,"doc-detail-140664-en":130},{"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":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","dairector-automatic-story-beat-generation-through-knowledge-synthesis","dAIrector - Automatic Story Beat Generation through Knowledge Synthesis","","dAIrector is an automated director that collaborates with human storytellers to support live improvisational performances and writing assistance. The system can generate short narrative arcs via contextual plot generation, producing story beats suitable for improvisation. The work details the system architecture, evaluates key design decisions with quantitative metrics, and reports a case study using qualitative feedback from a professional improvisational performer. Open-source code is provided for others to test and run the system.",{"@graph":69,"@context":122},[70,84,105],{"@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/dairector-automatic-story-beat-generation-through-knowledge-synthesis/140664/",{"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/dairector-automatic-story-beat-generation-through-knowledge-synthesis/140664.png","ImageObject",300,407,{"name":92,"@type":93},"Quinn","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-09-13","2026-08-24",true,{"@type":102,"interactionType":103,"userInteractionCount":14},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What is dAIrector designed to do in improvisational performances?","Question",{"text":112,"@type":113},"dAIrector acts as an automated director that collaborates with humans to generate story beats for live improvisational performance and provides writing assistance.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does dAIrector create narrative content?",{"text":117,"@type":113},"It creates short narrative arcs through contextual plot generation supported by knowledge graph synthesis.",{"name":119,"@type":110,"acceptedAnswer":120},"What kinds of evaluation does the paper present?",{"text":121,"@type":113},"The paper includes an architecture description, a quantitative evaluation of design choices, and a case study with qualitative feedback from a professional improvisational performer.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},140664,1787594558,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":14,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":52,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":129,"read_time":143},962075114765,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","dAIrector: Automatic Story Beat Generation through Knowledge Synthesis  \nMarkus Eger 1 and Kory W. Mathewson2,3  \n1 NC State University, Raleigh, NC, USA  \n2 University of Alberta, Edmonton, Alberta, Canada  \n3 HumanMachine, London, United Kingdom  \n[meger@ncsu.edu](meger@ncsu.edu), [korymath@gmail.com](korymath@gmail.com)  \nAbstract  \ndAIrector is an automated director which collaborates with humans sto  \nrytellers for live improvisational performances and writing assistance.  \ndAIrector can be used to create short narrative arcs through contex  \ntual plot generation. In this work, we present the system architecture, a  \nquantitative evaluation of design choices, and a case-study usage of the  \nsystem which provides qualitative feedback from a professional impro  \nvisational performer. We present relevant metrics for the understudied domain of human-machine creative generation, speci􀀌cally long-form narrative creation. We include, alongside publication, open-source code  \nso that others may test, evaluate, and run the dAIrector.  \n1 Introduction  \nImprovisational theatre (improv) is an art form in which narratives are developed ad-hoc in front of a live audience [Joh79] . Performers are prompted with a concise, ambiguous suggestion (e.g. a location or character relationship) and then share narrative development through action and dialogue. Often these prompts are provided by the audience throughout a performance. The most interesting challenge of improvisation is incorporating new suggestions, seemingly unrelated to the narrative. Improvisation's live justi􀀌cation has been proposed as a model for real-time dynamic problem solving [M+ 09, Ste11] . Improv has been proposed as a grand challenge for machine learning systems [MHR16] potentially as an extension to the Turing Test [Tur50, MM17a] . The dAIrector collaborates with human improvisors for semi-automated story beat generation, suitable for improvisation performance, through knowledge graph synthesis. First, we describe some background on story generation, improvisational theatre, and plot graphs (from Plotto and TV Tropes) . Then, we describe our approach and present quantitative and qualitative evaluation. We conclude with discussion of limitations and future work.  \n2 Background and Related Work  \n2.1 Automated Story Generation  \nThe research problem of automated story generation (ASG) is concerned with generating a sequence which collectively form a narrative [Mee76, Coo28] . The sequence can be composed of abstract concepts such as events or actions, or concrete text-based elements such as paragraphs, sentences, words, or characters. Di􀀋erent levels of abstraction and concreteness are accompanied by di􀀋erent challenges. For instance, stories de􀀌ned at high levels of abstraction maintain step-to-step coherence easier but are simpli􀀌ed and lack unique, speci􀀌c details.  \nCopyright 􀀍c by M. Eger, K. Mathewson. Copying permitted for private and academic purposes.  \nIn: H. Wu, M. Si, A. Jhala (eds.): Proceedings of the Joint Workshop on Intelligent Narrative Technologies and Workshop on  \nIntelligent Cinematography and Editing, Edmonton, Canada, 11-2018, published at [http://ceur-ws.org](http://ceur-ws.org)  \nPrevious ASG systems have used symbolic planning and extensive hand-engineering [RY10] . Open story generation systems use machine learning techniques to learn representations of the domain from the training data and incorporate knowledge from an external corpus [LLUJR13] . Martin et al. [MAW + 17] address the abstraction level challenges by using recurrent neural networks (RNNs) and an event representation to provide a level of abstraction between words and sentences capable of modelling narrative over hundreds of steps. They provide a method of pre-processing textual data into event sequences and then evaluate their event-to-event and event-to-sentence models. Our methods are distinct from this technique as we do not focus on the problem of sentence generation from ","cbCaivc0tkFUVgOk","https://ap.wps.com/l/cbCaivc0tkFUVgOk","pdf",436198,"English","# Introduction\n# Background and Related Work\n## Automated Story Generation\n## Digital Storytelling","[{\"question\":\"What is dAIrector designed to do in improvisational performances?\",\"answer\":\"dAIrector acts as an automated director that collaborates with humans to generate story beats for live improvisational performance and provides writing assistance.\"},{\"question\":\"How does dAIrector create narrative content?\",\"answer\":\"It creates short narrative arcs through contextual plot generation supported by knowledge graph synthesis.\"},{\"question\":\"What kinds of evaluation does the paper present?\",\"answer\":\"The paper includes an architecture description, a quantitative evaluation of design choices, and a case study with qualitative feedback from a professional improvisational performer.\"}]","dAIrector - Automatic Story Beat Generation through Knowledge Synthesis | PDF",25]