[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-156976-105":59,"doc-detail-156976-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","chapter-ordering-in-novels-paper","Chapter Ordering in Novels - Paper","","Chapter ordering in novels addresses how to recover narrative flow and text coherence across long-form documents where chapter sequence drives story understanding. The paper introduces a novel task: reconstructing the original chapter order from a random permutation of chapters in text. It frames reconstruction as a constraint-solving optimization using minimum feedback arc set and traveling salesman problem criteria with graph weights derived from RoBERTa-based relational scores from character occurrences and chapter-boundary detection. Experiments on 9,007 Project Gutenberg novels (avg. ~20 chapters) achieve a Spearman correlation of 0.59 above baseline.",{"@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/chapter-ordering-in-novels-paper/156976/",{"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/chapter-ordering-in-novels-paper/156976.png","ImageObject",300,407,{"name":92,"@type":93},"Đào","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-19","2026-08-29",true,{"@type":102,"interactionType":103,"userInteractionCount":44},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What is the chapter ordering task proposed in the paper?","Question",{"text":112,"@type":113},"It reconstructs the original order of novel chapters given an input random permutation of the chapters, aiming to recover narrative coherence across long-form text.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"Why can’t existing sentence ordering methods be directly applied to chapter ordering?",{"text":117,"@type":113},"Chapters are far longer than sentence sequences and contain many sentences, and the chapter count per novel is much larger than sentence counts in typical datasets, which degrades models on longer sequences.",{"name":119,"@type":110,"acceptedAnswer":120},"How is the chapter order reconstruction formulated for optimization?",{"text":121,"@type":113},"The approach builds a weighted directed graph with coherence scores for chapter pairs and reconstructs the permutation using optimization criteria combining the traveling salesman problem (TSP) and minimum arc feedback set.","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},156976,1787970664,{"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":44,"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":144,"preview_page_count":4},1374402968488,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","Chapter Ordering in Novels  \nAllen Kim, Steven Skiena  \nDepartment of Computer Science, Stony Brook University, NY, USA {allekim,[skiena}@cs.stonybrook.edu](skiena}@cs.stonybrook.edu)  \nAbstract  \nUnderstanding narrative flow and text coherence in long-form documents (novels) remains an open problem in NLP. To gain insight, we explore the task of chapter ordering, reconstructing the original order of chapters in novel given a random permutation of the text. This can be seen as extending the well-known sentence ordering task to vastly larger documents:  \nour task deals with over 9,000 novels with an average of twenty chapters each, versus standard sentence ordering datasets averaging only 5-8 sentences. We formulate the task of reconstructing order as a constraint solving problem, using minimum feedback arc set and traveling salesman problem optimization criteria, where the weights of the graph are generated based on models for character occurrences and chapter boundary detection, using relational chapter scores derived from RoBERTa. Our best methods yield a Spearman correlation of 0.59 on this novel and challenging task, substantially above baseline.  \n1 Introduction  \nNovels are a fundamental long-form medium for storytelling, requiring understanding of narrative flow for full comprehension of the text. Although neural network-based language models demonstrate amazing performance in comprehending short text windows, the problems of understanding long-form narrative texts such as summarization remain largely open.  \nA major challenge in research on long-form narration is the cost of annotation: the mere act of reading a novel generally requires a 10-15 hour commitment on the part of the annotator, making it clearly cost prohibitive to obtain full annotations of a significant corpus of novels. Although published summaries are available for up to a few hundred popular books, annotation cost is the rate limiting step for work in this area (Wu et al., 2021) .  \nIn this paper, we propose a new task that gets to the heart of narrative flow analysis for novels, without the need for human annotation. Most novels are partitioned into chapters as a means of providing thematic breakpoints for the reader. Randomly permuting the order of these chapters obviously ruins the coherence of the narrative flow of the underlying story. Here we propose the new task of chapter ordering: reconstructing the original order of the book given an input random chapter permutation of the text.  \nThis task is clearly related to the task of sentence ordering (Lapata, 2003 ; Barzilay and Lapata, 2005, 2008), reconstructing a set of sentences in a tiny story as to maximize their coherence. While there is a large volume of prior work on sentence ordering, to our knowledge, this is the first paper to address chapter ordering. The natural approaches for the sentence task cannot be readily applied to chapter order. First, chapters in novels usually contain several hundred sentences, which cannot easily be encoded with the neural models applied to sentence ordering. Second, the number of chapters in a novel (an average of 21.6 chapters/novel in our corpus) versus 5 to 8 sentences in popular datasets. This matters, because the impressive performances of the best sentence ordering models show severe degradation with longer sequences. Finally, ordering sentences in a tiny story is a simpler perceptual task for humans, whereas correctly ordering the chapters of even a single novel requires hours of reading and analysis. The combination of these factors makes chapter ordering a difficult task that cannot be tackled with standard methods. The overview of our approach can be found in Figure 1.  \nIn this paper, we define the chapter ordering problem and propose a variety of neural-based models to score the relative order of chapter-pairs. Our main contributions 1 include:  \n1Code and link to dataset found at [https://github.com/](https://github.com/)[ ](https://github.com/)","cbCaiuMZhyXJUICO","https://ap.wps.com/l/cbCaiuMZhyXJUICO","pdf",363205,11,"English","# Introduction\n## Chapter ordering as a new task\n## Relation to sentence ordering\n# Problem definition and contributions\n## Chapter-ordering dataset\n## Neural coherence models","[{\"question\":\"What is the chapter ordering task proposed in the paper?\",\"answer\":\"It reconstructs the original order of novel chapters given an input random permutation of the chapters, aiming to recover narrative coherence across long-form text.\"},{\"question\":\"Why can’t existing sentence ordering methods be directly applied to chapter ordering?\",\"answer\":\"Chapters are far longer than sentence sequences and contain many sentences, and the chapter count per novel is much larger than sentence counts in typical datasets, which degrades models on longer sequences.\"},{\"question\":\"How is the chapter order reconstruction formulated for optimization?\",\"answer\":\"The approach builds a weighted directed graph with coherence scores for chapter pairs and reconstructs the permutation using optimization criteria combining the traveling salesman problem (TSP) and minimum arc feedback set.\"}]","Chapter Ordering in Novels - Paper | PDF",28]