[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-154304-105":59,"doc-detail-154304-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","creative-help-a-story-writing-assistant","Creative Help - A Story Writing Assistant","","Creative Help is a web-based story writing assistant that generates suggestions for the next sentence while a user is drafting a narrative. Writers can modify or delete each suggestion to preserve authorship and control over the unfolding plot. The system records users’ edits to quantify perceived helpfulness, using edit distance between a suggestion and its resulting modification. Different suggestion-generation models are compared to evaluate effectiveness, showing case-based reasoning can produce more helpful suggestions than random choices.",{"@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":30,"@type":76,"position":81},"https://docshare.wps.com/document/technology/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/creative-help-a-story-writing-assistant/154304/",{"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/creative-help-a-story-writing-assistant/154304.png","ImageObject",300,407,{"name":92,"@type":93},"Quinn","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-05","2026-08-28",true,{"@type":102,"interactionType":103,"userInteractionCount":29},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What does Creative Help generate while users write a story?","Question",{"text":112,"@type":113},"It generates a suggestion for the next sentence, based on a “help” request entered by the writer.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does the system measure whether a suggestion is helpful?",{"text":117,"@type":113},"It tracks how users revise or delete suggested sentences, using similarity and edit distance between the original suggestion and the user’s modification.",{"name":119,"@type":110,"acceptedAnswer":120},"How is the next-sentence suggestion generated?",{"text":121,"@type":113},"The backend uses a generation model that retrieves relevant suggestions from a large corpus of existing stories, using a case-based reasoning approach.","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},154304,1787890708,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":29,"category_name":30,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":29,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":129,"read_time":41},962075114765,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","Creative Help: A Story Writing Assistant  \nMelissa Roemmele and Andrew S. Gordon  \nInstitute for Creative Technologies  \nUniversity of Southern California  \nLos Angeles, CA, USA  \n[roemmele@ict.usc.edu](roemmele@ict.usc.edu), [gordon@ict.usc.edu](gordon@ict.usc.edu)  \nAbstract. We present Creative Help, an application that helps writers by generating suggestions for the next sentence in a story as it being written. Users can modify or delete suggestions according to their own vision of the unfolding narrative. The application tracks users' changes to suggestions in order to measure their perceived helpfulness to the story, with fewer edits indicating more helpful suggestions. We demonstrate how the edit distance between a suggestion and its resulting modi􀀌cation can be used to comparatively evaluate di􀀋erent models for generating suggestions. We describe a generation model that uses case-based reasoning to  \n􀀌nd relevant suggestions from a large corpus of stories. The application shows that this model generates suggestions that are more helpful than randomly selected suggestions at a level of marginal statistical signi􀀌 -cance. By giving users control over the generated content, Creative Help provides a new opportunity in open-domain interactive storytelling.  \nKeywords: open-domain interactive narrative 􀀁 writing aids 􀀁 natural language generation  \n1 Introduction  \nThe 􀀌eld of arti􀀌cial intelligence has long conceived of using computers to write stories. The 􀀌rst known automated story generation system, Novel Writer, was developed in 1973 [7], followed by a steady line of work up to the present [e.g. 8, 13, 15] . These systems act as writing agents that generate narratives from hand-authored models of the characters, settings, and actions comprising the story-world domain. Similarly, there are works of 􀀌ction generated through user interaction, with these 􀀌rst of these systems, Adventure, emerging in 1975 [2] . Despite the apparent user-driven nature of interactive 􀀌ction systems, they are similar to the AI systems in their autonomy. They expect users' writing to adhere to a highly constrained syntax and vocabulary in order to continue the emerging narrative. They also similarly rely on hand-authored domain models that push users towards one of a limited number of prede􀀌ned experiences. The current challenge for narrative AI is to provide interactivity that gives human authors control over writing, enabling them to write the stories they want to tell.  \nOne of the barriers to advancing true interactivity is automatically understanding the author's intended meaning as the story is being written. Advancesin the 􀀌eld of natural language processing are starting to break down this barrier. Many emerging language technologies can be seen as assistive tools that recognize users' intent and help them achieve it. Automated spelling and grammar correction, as commonplace as they seem, are examples of simple writing aids. We envision a new sort of writing aid, one that performs \\narrative autocompletion\": it analyzes a story as it is being written and then makes a suggestion for how to continue the story.  \nRecent work in open-domain interactive storytelling now supports this vision. The impracticality of authoring models for every possible story domain has motivated the e􀀋ort to learn such models from data [1, 11] . Swanson and Gordon [19] describe a case-based reasoning approach for generalizing knowledge from existing stories to new ones. They present this approach as Say Anything, a platform where the user and automated agent take turns writing sentences in a story. The success of this system in producing readable stories established a new path towards users having authorial control in interactive narrative experiences.  \nIn this paper, we present Creative Help, a system that builds on Swanson and Gordon's story generation approach [19], but is unique in its role as an assistive tool that places the writer in control of the resulti","cbCaitygjuGICiEs","https://ap.wps.com/l/cbCaitygjuGICiEs","pdf",367138,12,"English","# Introduction\n## Narrative autocompletion and assistive writing\n## Case-based reasoning for suggestion generation\n## Evaluation via user edits\n# Creative Help\n## Web-based interface and help requests\n## Backend generation from story corpora\n## User editing and iterative continuation","[{\"question\":\"What does Creative Help generate while users write a story?\",\"answer\":\"It generates a suggestion for the next sentence, based on a “help” request entered by the writer.\"},{\"question\":\"How does the system measure whether a suggestion is helpful?\",\"answer\":\"It tracks how users revise or delete suggested sentences, using similarity and edit distance between the original suggestion and the user’s modification.\"},{\"question\":\"How is the next-sentence suggestion generated?\",\"answer\":\"The backend uses a generation model that retrieves relevant suggestions from a large corpus of existing stories, using a case-based reasoning approach.\"}]","Creative Help - A Story Writing Assistant | PDF"]