Semantic Similarity Relaxation and Approximation of Incomplete Queries Using LLMs Embedding to Topic Graph Mining

Semantic Similarity Relaxation and Approximation of Incomplete Queries Using LLMs Embedding to Topic Graph Mining | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Semantic Similarity Relaxation and Approximation of Incomplete Queries Using LLMs Embedding to Topic Graph Mining Hayam Aboelmaged Hussin, Karam Gouda, Mona Arafa, Walaa Medhat This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4999649/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract In recent years, the Resource Description Framework (RDF) has emerged as a pivotal technology for structuring and interlinking data on the web. RDF graphs typically have billions of labelled entities, and how to efficiently retrieve the needed information from an RDF KG for a given SPARQL query has recently drawn more attention. However, because RDF data is schema-free, it is very challenging for users to understand the underlying structure fully. Consequently, different graph fragments can represent the same information. Therefore, it is extremely challenging to create complex SPARQL queries that encompass all possible structures. Recently, researchers have started to use knowledge semantics to extend the query intention of a simplified query to get an approximate answer. In this paper, we present an efficient framework that allows access to the RDF repository even if users lack comprehensive knowledge of the underlying schema. Based on semantic similarity, we can get more answers that match the simple query. We propose a systematic method to mine RDF graphs into diverse semantically equivalent structure patterns (topic graphs). We use type similarity to construct these patterns, and then a large language model (LLM) embedding is adapted to these patterns to achieve semantic vectors of existing knowledge. Based on the knowledge semantics above, an approximate query is constructed to get the top-k semantic similarity result. Extensive testing using the DBpedia dataset and QALD-4 benchmark query has proven how effective and efficient our approach is. Topic graph mining LLMs knowledge graph embedding Approximation of query Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-4999649","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":356704632,"identity":"08ab962d-b70d-4108-a9da-b4b93c80864c","order_by":0,"name":"Hayam Aboelmaged Hussin","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABFklEQVRIie2RMUvDQBTHXymYJabrG9R8hZOArfTLXCg0yzMUumQoclMyiWsH8UsIzm0D6XKCY9x0z1DoKuK7toLDWTsK3g8O3oP78X/vDsDh+IMIPjMAlAA+F9kZHHHBtA9VdHSYYtgo0MojgN+ULg7eFjX00m7xNF+83IswgOMKIevHyiuebcrldChKAhyf6FSWV4/iPIdgiKCTWPl6ZB2slhslngIJVt4l73KBrbyMFZK0K8lqq3QaVu7ETvlgJWx+UGiXgiZFfSnKpHgzq6KbUUkCx4icQhXv0g4GPVklUe6T9cXEMnlYU3adYoeiNU1EGBY383o16Z/eestXq7MVvzfmR8wSPKGw3t6HtyfF4XA4/hGfUCldwZA+2AQAAAAASUVORK5CYII=","orcid":"","institution":"Benha University","correspondingAuthor":true,"prefix":"","firstName":"Hayam","middleName":"Aboelmaged","lastName":"Hussin","suffix":""},{"id":356704633,"identity":"82189c7e-765f-4a6d-a2f7-bc9705cd5723","order_by":1,"name":"Karam Gouda","email":"","orcid":"","institution":"Benha University","correspondingAuthor":false,"prefix":"","firstName":"Karam","middleName":"","lastName":"Gouda","suffix":""},{"id":356704636,"identity":"f970ebed-6081-4f87-bfe7-4f12b6136843","order_by":2,"name":"Mona Arafa","email":"","orcid":"","institution":"Benha University","correspondingAuthor":false,"prefix":"","firstName":"Mona","middleName":"","lastName":"Arafa","suffix":""},{"id":356704639,"identity":"6501f611-d925-4c41-94fa-8984c6f828d0","order_by":3,"name":"Walaa Medhat","email":"","orcid":"","institution":"Benha University","correspondingAuthor":false,"prefix":"","firstName":"Walaa","middleName":"","lastName":"Medhat","suffix":""}],"badges":[],"createdAt":"2024-08-29 18:57:43","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4999649/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4999649/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":66049738,"identity":"1418fe7f-a787-4a29-8221-229b5f9947e4","added_by":"auto","created_at":"2024-10-07 08:02:00","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":777659,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4999649/v1_covered_044c594b-4a2c-4bdd-bd13-604e4911ad2b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Semantic Similarity Relaxation and Approximation of Incomplete Queries Using LLMs Embedding to Topic Graph Mining","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Topic graph mining, LLMs, knowledge graph embedding, Approximation of query","lastPublishedDoi":"10.21203/rs.3.rs-4999649/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4999649/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn recent years, the Resource Description Framework (RDF) has emerged as a pivotal technology for structuring and interlinking data on the web. RDF graphs typically have billions of labelled entities, and how to efficiently retrieve the needed information from an RDF KG for a given SPARQL query has recently drawn more attention. However, because RDF data is schema-free, it is very challenging for users to understand the underlying structure fully. Consequently, different graph fragments can represent the same information. Therefore, it is extremely challenging to create complex SPARQL queries that encompass all possible structures. Recently, researchers have started to use knowledge semantics to extend the query intention of a simplified query to get an approximate answer.\u003c/p\u003e \u003cp\u003eIn this paper, we present an efficient framework that allows access to the RDF repository even if users lack comprehensive knowledge of the underlying schema. Based on semantic similarity, we can get more answers that match the simple query. We propose a systematic method to mine RDF graphs into diverse semantically equivalent structure patterns (topic graphs). We use type similarity to construct these patterns, and then a large language model (LLM) embedding is adapted to these patterns to achieve semantic vectors of existing knowledge. Based on the knowledge semantics above, an approximate query is constructed to get the top-k semantic similarity result. Extensive testing using the DBpedia dataset and QALD-4 benchmark query has proven how effective and efficient our approach is.\u003c/p\u003e","manuscriptTitle":"Semantic Similarity Relaxation and Approximation of Incomplete Queries Using LLMs Embedding to Topic Graph Mining","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-09-30 08:34:46","doi":"10.21203/rs.3.rs-4999649/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"25614c40-4565-472a-86e7-210b80168b6a","owner":[],"postedDate":"September 30th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-10-07T07:53:52+00:00","versionOfRecord":[],"versionCreatedAt":"2024-09-30 08:34:46","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4999649","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4999649","identity":"rs-4999649","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}