[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-320571-105":59,"doc-detail-320571-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","question-answering-system-for-legal-bar-examination-using-predicate-argument-structure","Question Answering System for Legal Bar Examination using Predicate Argument Structure","","Developed a question answering system for the legal bar examination that explains solutions through underlying logical structures, focusing on predicate argument structure (subject-object with predicates) to model legal-document structure. Implemented multiple modules with different retrieval strategies and combined them using SVM-based confidence learning. Built a legal-domain structured synonym dictionary by categorizing predicates with their objects to handle superficial predicate variations without external knowledge. Verified performance on simple problems and achieved the second-best score in Task 4 of the COLIEE 2018 shared task.",{"@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/question-answering-system-for-legal-bar-examination-using-predicate-argument-structure/320571/",{"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/question-answering-system-for-legal-bar-examination-using-predicate-argument-structure/320571.png","ImageObject",300,407,{"name":92,"@type":93},"4398046744996","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-02","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":52},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What logical structure does the system use to represent legal document information?","Question",{"text":112,"@type":113},"It focuses on the predicate argument structure, i.e., the subject-object relations governed by predicates, to capture structures of legal documents.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How are results produced from different searching modules?",{"text":117,"@type":113},"The system combines outputs from multiple modules by learning each module’s confidence value with SVM.",{"name":119,"@type":110,"acceptedAnswer":120},"What is the role of the structured synonym dictionary?",{"text":121,"@type":113},"It maps predicate variants by organizing predicates according to the objects they can take, absorbing superficial differences for problems that do not require external knowledge.","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},320571,1791004070,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":66,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":133,"file_id":134,"file_url":135,"file_type":136,"file_size":137,"view_count":52,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":138,"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":143,"read_time":41,"preview_page_count":4},4398046744996,"Question Answering System for Legal Bar Examination using Predicate Argument Structure  \nReina Hoshino 1, Ryosuke Taniguchi 1, Naoki Kiyota 1 , and Yoshinobu Kano1  \n1 Informatics Course, Graduate School of Integrated Science and Technology, Shizuoka University, 3-5-1 Johoku, Naka-ku, Hamamatsu City, Japan  \n[rhoshino@kanolab.net](rhoshino@kanolab.net), [rtaniguchi@kanolab.net](rtaniguchi@kanolab.net)  \n[nkiyota@kanolab.net](nkiyota@kanolab.net), [kano@inf.shizuoka.ac.jp](kano@inf.shizuoka.ac.jp)  \nAbstract. We developed a question answering system for legal bar exam, which can explain the way system solves based on underlying logical structures. We focus on the set of subject and object with their predicate, i.e. the predicate argument structure, in order to represent structures of legal documents. We implemented a couple of modules using different searching methods. Our system outputs results using these modules by learning each module’s confidence value with SVM. We manually analyzed the difficulty level of the problems whether external knowledge is required or not. We created a structured synonym dictionary specialized to the legal domain, where predicates are categorized with their objects. This synonym dictionary could absorb superficial differences of predicates to solve the problems which do not require external knowledge. We confirmed that the system can solve more than 70 percent of simple problems. Our system achieved the second best score in Task 4 of the COLIEE 2018 shared task.  \nKeywords: COLIEE, Question Answering, Legal Bar Exam, Legal Information Extraction, Predicate Argument Structure Analysis.  \n1 Introduction  \nAutomatic question answering for legal documents is gathering attention recently. This paper describes our challenge to Task 4 of the COLIEE 2018 legal bar exam, which asks participants to answer true or not based on the Civil Law Articles, given text drawn from the Japanese legal bar exam.  \nThe COLIEE shared task series is held in association with the JURISIN (Jurisinformatics) workshop. The first one was the COLIEE 2014 shared task[1] . Following this, COLIEE 2015 shared task[2], COLIEE2016 shared task[3], and COLIEE 2017[4] .shared task (this time in conjunction with ICAIL) were held. The COLIEE shared task consists of four tasks. We challenged Task four. Task one and Task two used the legal cases. Task one of this legal question answering task involves reading a legal bar exam question, and extracting a subset of Japanese Civil Code Articles. Task four requires both of the legal information retrieval system and textual entailment system. Given a set of legal yes/no questions, a participant’s system will retrieve rele-  \nvant Civil Law articles. Then answer yes/no entailment relationship between input yes/no question and the retrieved articles. The corpus of legal questions is drawn from Japanese Legal Bar exams, and the relevant Japanese Civil Law articles were also provided. While there was an English translation version of the dataset provided, we only used the original Japanese version.  \nRegarding question answering in general, most successful systems employ rather traditional techniques of question answering which have decades of history [5]–[8] . Recently, automatic answering system used machine learning by big data. The typical example is IBM Watson System [9] . The core Watson system employed a couple of open source libraries, including the traditionally well-designed DeepQA system [10] as its skeleton of question answering processing.  \nHowever, there are only hundreds of problem sentences used in COLIEE. We think that the amount of data is not enough to perform an end-to-end supervised machine learning. There are an enormous number of legal documents, many methods have been proposed to acquire knowledge from case examples [11] . However, it is difficult to use case examples directly in the legal bar exam, because we need commonsense knowledge to follow the thinking of a legal expert,","cbCaiulcPnHDftk3","https://ap.wps.com/l/cbCaiulcPnHDftk3","pdf",524975,12,"English","# 1 Introduction\n## COLIEE shared task and Task 4 setup\n## Related work on question answering systems\n## Challenges and motivations\n## Key issues in legal reasoning and language","[{\"question\":\"What logical structure does the system use to represent legal document information?\",\"answer\":\"It focuses on the predicate argument structure, i.e., the subject-object relations governed by predicates, to capture structures of legal documents.\"},{\"question\":\"How are results produced from different searching modules?\",\"answer\":\"The system combines outputs from multiple modules by learning each module’s confidence value with SVM.\"},{\"question\":\"What is the role of the structured synonym dictionary?\",\"answer\":\"It maps predicate variants by organizing predicates according to the objects they can take, absorbing superficial differences for problems that do not require external knowledge.\"}]","Question Answering System for Legal Bar Examination using Predicate Argument Structure | PDF",1789950190]