[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-201216-105":59,"doc-detail-201216-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","adalogn-adaptive-logic-graph-network-for-reasoning-based-machine-reading-comprehension-abstract","AdaLoGN - Adaptive Logic Graph Network for Reasoning-Based Machine Reading Comprehension - Abstract","","Recent machine reading comprehension datasets such as ReClor and LogiQA require logical reasoning over text. Conventional neural models fall short of capturing discrete logic, while symbolic reasoners cannot directly operate on raw text. AdaLoGN introduces a neural-symbolic graph framework that passes messages over a logic-structured graph of text units, adaptively extending logical relations and enabling mutual reinforcement between neural and symbolic reasoning. A subgraph-to-node mechanism improves context-option interaction for multiple-choice answering, achieving promising results.",{"@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/adalogn-adaptive-logic-graph-network-for-reasoning-based-machine-reading-comprehension-abstract/201216/",{"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/adalogn-adaptive-logic-graph-network-for-reasoning-based-machine-reading-comprehension-abstract/201216.png","ImageObject",300,407,{"name":92,"@type":93},"Alex Sinclair","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-16","2026-09-04",true,{"@type":102,"interactionType":103,"userInteractionCount":24},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does AdaLoGN address in machine reading comprehension?","Question",{"text":112,"@type":113},"It targets MRC datasets where answering requires logical reasoning over relations expressed in text, such as implication and negation.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does AdaLoGN combine neural and symbolic reasoning?",{"text":117,"@type":113},"AdaLoGN builds a text logic graph and performs message passing while adaptively inferring and extending logical relations so neural reasoning and symbolic reasoning reinforce each other iteratively.",{"name":119,"@type":110,"acceptedAnswer":120},"What mechanism improves performance on multiple-choice questions?",{"text":121,"@type":113},"It uses a novel subgraph-to-node message passing mechanism to strengthen interaction between context and options when selecting among multiple choices.","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},201216,1790563951,{"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":24,"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":144,"read_time":145},1099523882182,"https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8","AdaLoGN: Adaptive Logic Graph Network for Reasoning-Based Machine Reading Comprehension  \nXiao Li and Gong Cheng and Ziheng Chen and Yawei Sun and Yuzhong Qu State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China {xiaoli.nju,chenziheng,[ywsun}@smail.nju.edu.cn](ywsun}@smail.nju.edu.cn)[ ](ywsun}@smail.nju.edu.cn){gcheng,[yzqu}@nju.edu.cn](yzqu}@nju.edu.cn)  \nAbstract  \nRecent machine reading comprehension datasets such as ReClor and LogiQA require performing logical reasoning over text. Conventional neural models are insufficient for logical reasoning, while symbolic reasoners cannot directly apply to text. To meet the challenge, we present a neural-symbolic approach which, to predict an answer, passes messages over a graph representing logical relations between text units. It incorporates an adaptive logic graph network (AdaLoGN) which adaptively infers logical relations to extend the graph and, essentially, realizes mutual and iterative reinforcement between neural and symbolic reasoning. We also implement a novel subgraph-to-node message passing mechanism to enhance context-option interaction for answering multiple-choice questions. Our approach shows promising results on ReClor and LogiQA.  \n1 Introduction  \nMachine reading comprehension (MRC) has drawn much research attention. Early MRC datasets are not difficult for state-of-the-art neural methods. Indeed, BERT (Devlin et al., 2019) has outperformed humans on SQuAD (Rajpurkar et al., 2016) . Recent datasets become more challenging. For example, ReClor (Yu et al., 2020) and LogiQA (Liu et al., 2020) require understanding and reasoning over logical relations described in text, where neural methods showed unsatisfactory performance.  \nFor instance, consider the MRC task in Figure 1. The context consists of a set of textual propositions describing logical relations between elementary discourse units (EDUs) (Mann and Thompson, 1988) . For example, the first sentence describes an implication between two EDUs: “the company gets project A” implies that “product B can be put on the market on schedule”. With the help of propositional calculus, humans can formalize propositions and then apply inference rules in proposi-  \nContext: If the company gets project A, product B can be put on the market on schedule. Product B is put on schedule if and only if the company’s fund can be normally turned over. If the company’s fund cannot be turned over normally, the development of product C cannot be carried out as scheduled. The fact is that the development of product C is carried out as scheduled.  \nQuestion: This shows:  \nOptions:  \nA. The company gets project A and product B is put on the market on schedule.  \nB. The company does not get project A and product B is not put on the market on schedule.  \n. Product B is put on the market on schedule and the company’s fund is turned over normally.  \nD. Product B is not put on the market on schedule, and the company’s fund turnover is extremely abnormal.  \nFigure 1: An example MRC task (adapted from a task in LogiQA) . Logical connectives are highlighted in italics. Xmarks the correct answer.  \ntional logic to prove the proposition in option C. However, how can machines solve such a task?  \nExisting Methods and Limitations To solve it, conventional neural models are insufficient for providing the required reasoning capabilities, while symbolic reasoners cannot directly apply to unstructured text. One promising direction is to consider a neural-symbolic solution, such as the recent DAGN method (Huang et al., 2021a) . It breaks down the context and each option into a set of EDUs and connects them with discourse relations as a graph. Then it performs graph neural network (GNN) based reasoning to predict an answer.  \nHowever, we identify two limitations in this method. L1: Despite the graph representation, it is predominantly a neural method over discourse relations. It is debatable whether the required symbolic reasoning","cbCaisDd4RtLxDer","https://ap.wps.com/l/cbCaisDd4RtLxDer","pdf",2346502,15,"English","# Introduction\n## Existing Methods and Limitations\n## Our Approach\n# Problem Illustration\n## Example MRC Task\n## Two TLGs for the Approach","[{\"question\":\"What problem does AdaLoGN address in machine reading comprehension?\",\"answer\":\"It targets MRC datasets where answering requires logical reasoning over relations expressed in text, such as implication and negation.\"},{\"question\":\"How does AdaLoGN combine neural and symbolic reasoning?\",\"answer\":\"AdaLoGN builds a text logic graph and performs message passing while adaptively inferring and extending logical relations so neural reasoning and symbolic reasoning reinforce each other iteratively.\"},{\"question\":\"What mechanism improves performance on multiple-choice questions?\",\"answer\":\"It uses a novel subgraph-to-node message passing mechanism to strengthen interaction between context and options when selecting among multiple choices.\"}]","AdaLoGN - Adaptive Logic Graph Network for Reasoning-Based Machine Reading Comprehension - Abstract | PDF",1788527752,38]