[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124712-en":3,"doc-seo-124712-105":30,"detail-sidebar-cat-0-en-105":83},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},124712,8796095360427,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Using Machine Learning for Automated Detection of Ambiguity in Building Requirements","Rule interpretation in compliance checking remains insufficiently automated, limiting full automation of the compliance process in the AEC domain. Prior work supports automated interpretation of building requirements but cannot identify or handle ambiguous clauses. This study proposes a supervised machine learning approach to detect ambiguity automatically, achieving recall, precision, and accuracy of 99.0%, 71.1%, and 78.2%. The method advances automated detection of ambiguity to enable automated compliance checking.","USING MACHINE LEARNING FOR AUTOMATED DETECTION OF AMBIGUITY IN  \nBUILDING REQUIREMENTS  \nZijing Zhang 1, Ling Ma1  \n1University College London, London, UK  \nAbstract  \nThe rule interpretation step is yet to be fully automated in the compliance checking process, which hinders the automation of compliance checking. Whilst existing research has developed numerous methods for automated interpretation of building requirements, none of them can identify or address ambiguous requirements. As part of interpreting ambiguous clauses automatically, this research proposed a supervised machine learning method to detect ambiguity automatically, where the bestperforming model achieved recall, precision and accuracy scores of 99.0%, 71.1%, and 78.2%, respectively. This research contributes to the body of knowledge by developing a method for automated detection of ambiguity in building requirements to support automated compliance checking.  \nIntroduction  \nIn the architecture, engineering and construction (AEC) industry, compliance checking is an important step where the building design is checked against requirements in building regulatory documents, recommendations and guidance (Eastman et al., 2009) . Traditional compliance checking is laborious, costly, time-consuming and errorprone (Eastman et al., 2009; Macit İlal & Günaydın, 2017; Zhang et al., 2022a) . To address this issue, automated compliance checking (ACC) has been a research focus in the past years. Numerous studies have proposed methods to address different aspects of the ACC challenges, including the rule interpretation and representation to a computer-readable form (Hjelseth & Nisbet, 2011; Solihin & Eastman, 2016; Yurchyshyna & Zarli, 2009; Zhang et al., 2023), the preparation of the building design model data for checking (Solihin et al., 2020), and the development of the automated compliance checking system (Kim et al., 2020; Pauwels et al., 2011) .  \nDespite the research interest, the rule interpretation and representation step remains a bottleneck in the ACC process. Many existing methods (such as the RASE method (Hjelseth & Nisbet, 2011)) still rely on a manual or semi-automated rule interpretation, which requires extensive efforts by domain experts (Zhang & El-Gohary Nora, 2017) . More recently, some automated methods, mainly based on machine learning, have been proposed and achieved satisfying performance. However, they can  \nonly deal with quantitative clauses or qualitative rules with attributes; none can deal with rules with ambiguity.  \nAmbiguous rules are requirements that are open to more than one interpretation. For example, the rule “Additional space may be required for special baths.” is ambiguous asthe additional space required is not specified and there is no explanation of what baths are special. Ambiguity is a major factor hindering fully automated compliance checking (Zhang & El-Gohary, 2022) . To make matters worse, as reported by Soliman-Junior et al. (2021), up to 53% of building rules can be ambiguous, which is a considerable percentage and should be addressed.  \nThe automation of interpreting and representing ambiguous rules would first require accurate and fast identification of ambiguous clauses in building requirements. This paper thus aims to address this issue by using machine learning methods. Identifying ambiguous clauses would be the crucial first step towards automated interpreting and representing building requirement clauses.  \nThe remainder of this paper is structured as follows. The second section reviews related research. Then, the method used in this paper is proposed. Next, the results of this paper are presented, followed by discussions on the results. Finally, the paper offers some conclusions.  \nLiterature review  \nAmbiguity in natural language  \nAmbiguity is a phenomenon in natural language that has long been studied by linguists, philosophers and psychologists. Some early studies focused on understanding ambiguity by providing cla","cbCaib7IEegkzWgS","https://ap.wps.com/l/cbCaib7IEegkzWgS","pdf",242111,1,7,"English","en",105,"# Introduction\n# Literature review\n## Ambiguity in natural language","[{\"question\":\"How is ambiguity defined in building requirements?\",\"answer\":\"Ambiguous rules are requirements open to more than one interpretation, such as rules where key details are missing (e.g., unspecified amounts or unclear meanings of referenced facilities).\"}]","Using Machine Learning for Automated Detection of Ambiguity in Building Requirements | PDF",1785894052,18,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":78,"head_meta":80,"extra_data":82,"updated_unix":28},"using-machine-learning-for-automated-detection-of-ambiguity-in-building-requirements","",{"@graph":36,"@context":77},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/using-machine-learning-for-automated-detection-of-ambiguity-in-building-requirements/124712/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71],{"name":72,"@type":73,"acceptedAnswer":74},"How is ambiguity defined in building requirements?","Question",{"text":75,"@type":76},"Ambiguous rules are requirements open to more than one interpretation, such as rules where key details are missing (e.g., unspecified amounts or unclear meanings of referenced facilities).","Answer","https://schema.org",{"og:url":52,"og:type":79,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":81,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,111,114,119,122,126],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":46,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":112,"slug":113},30,"research-report",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":98,"slug":129},19,"General","general"]