Enhancing SPARQL Query Performance with Recurrent Neural Networks

Enhancing SPARQL Query Performance with Recurrent Neural Networks | 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 Enhancing SPARQL Query Performance with Recurrent Neural Networks YiHui Chen, Eric Jui-Lin Lu, Jin-De Lin This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-2676239/v4 This work is licensed under a CC BY 4.0 License Status: Posted Version 4 posted You are reading this latest preprint version Show more versions Abstract DBpedia is one of the most resourceful link databases today, and to access information in DBpedia databases, we need to use query syntax (e.g., SPARQL). However, not all users know SPARQL, so we must use a natural language query system to translate the user's query into the corresponding query syntax. It is costly and time-consuming for the query system to generate query syntax. Therefore, this paper proposes generating query syntax from natural language. Two multi-label learning methods are used for question transformation: Binary Relevance (BR) and Classifier Chains (CC). To predict all the labels that match the query intentions, we use Recurrent Neural Networks (RNNs) to build a multi-label classifier for generating RDF triples. To better consider the relationship between RDF triples, the Binary Relevance is integrated into an ensemble learning approach to propose an Ensemble BR. The experiments perform better than the other research to improve the query accuracy. (This article is accepted by IEEE Access with Digital Object Identifier: 10.1109/ACCESS.2023.3308691 entitled Enhancing SPARQL Query Performance with Recurrent Neural Networks) Artificial Intelligence and Machine Learning DBPedia SPARQL Question Answering Systems QALD LC-QuAD Multi-label classifier Recurrent Neural Network (RNN) Binary Relevance (BR) Classifier Chains (CC) Full Text Cite Share Download PDF Status: Posted Version 4 posted You are reading this latest preprint version Show more versions 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-2676239","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":230423158,"identity":"1db51464-54d3-4380-bd8b-b1f648076566","order_by":0,"name":"YiHui Chen","email":"","orcid":"https://orcid.org/0000-0002-9932-0594","institution":"Chang Gung University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"YiHui","middleName":"","lastName":"Chen","suffix":""},{"id":230423159,"identity":"ddabb69e-f3a7-4b24-b3c2-2afa0af6b34f","order_by":1,"name":"Eric Jui-Lin Lu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAArklEQVRIiWNgGAWjYBACxnbmBoYPDAwJII4EcVqaGRsYZyC0GBChh5mxgZmHJC3MzYxt0rY77PIMDjAfvM3D8CexgQiHtUnnnkkuNjjAlmzNw2BArJa2A4kbDvCYSQO15BKnxRKshf8bCVoYIbawEa2l2bK3LTlx5mE2Y8s5Bsb1BLUYtjcfvPGzzS6x73jzwxtvKuSMCelgMIQbygwiiIlJeSLUjIJRMApGwUgHAFbAN74VUbdlAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0001-7953-5486","institution":"National Chung Hsing University","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Eric","middleName":"Jui-Lin","lastName":"Lu","suffix":""},{"id":230423160,"identity":"185e7bca-0f75-433c-a743-4ab56021d9a2","order_by":2,"name":"Jin-De Lin","email":"","orcid":"","institution":"National Chung Hsing University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jin-De","middleName":"","lastName":"Lin","suffix":""}],"badges":[],"createdAt":"2023-03-10 05:23:50","currentVersionCode":4,"declarations":"","doi":"10.21203/rs.3.rs-2676239/v4","doiUrl":"https://doi.org/10.21203/rs.3.rs-2676239/v4","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":42660104,"identity":"058ae27d-49a8-456a-b7a6-9c6b711f738a","added_by":"auto","created_at":"2023-09-05 18:03:40","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":997408,"visible":true,"origin":"","legend":"","description":"","filename":"SoftComputing.pdf","url":"https://assets-eu.researchsquare.com/files/rs-2676239/v4_covered_aa79a703-8178-4045-9442-c1554c9c85dd.pdf"}],"financialInterests":"","formattedTitle":"\u003cp\u003eEnhancing SPARQL Query Performance with Recurrent Neural Networks\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[{"identity":"b3425fc8-61c8-4f80-b1c7-d92bf87c3f31","identifier":"10.13039/501100011892","name":"Kaohsiung Chang Gung Memorial Hospital","awardNumber":"CMRPD3N0011","order_by":0},{"identity":"bc5d66b6-8e9d-441b-996f-6d7b84f1fbbf","identifier":"10.13039/501100018537","name":"National Science and Technology Major Project","awardNumber":"110-2221-E-182 -026 -MY3","order_by":1}],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"National Science and Technology Council","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":"DBPedia, SPARQL, Question Answering Systems, QALD, LC-QuAD, Multi-label classifier, Recurrent Neural Network (RNN), Binary Relevance (BR), Classifier Chains (CC)","lastPublishedDoi":"10.21203/rs.3.rs-2676239/v4","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-2676239/v4","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cul\u003e\n \u003cli\u003eDBpedia is one of the most resourceful link databases today, and to access information in DBpedia databases, we need to use query syntax (e.g., SPARQL). However, not all users know SPARQL, so we must use a natural language query system to translate the user's query into the corresponding query syntax. It is costly and time-consuming for the query system to generate query syntax. Therefore, this paper proposes generating query syntax from natural language. Two multi-label learning methods are used for question transformation: Binary Relevance (BR) and Classifier Chains (CC). To predict all the labels that match the query intentions, we use Recurrent Neural Networks (RNNs) to build a multi-label classifier for generating RDF triples. To better consider the relationship between RDF triples, the Binary Relevance is integrated into an ensemble learning approach to propose an Ensemble BR. The experiments perform better than the other research to improve the query accuracy. (This article is accepted by IEEE Access with Digital Object\u003cstrong\u003e \u003c/strong\u003eIdentifier: 10.1109/ACCESS.2023.3308691 entitled Enhancing SPARQL Query Performance with Recurrent Neural Networks)\u003c/li\u003e\n\u003c/ul\u003e","manuscriptTitle":"Enhancing SPARQL Query Performance with Recurrent Neural Networks","msid":"","msnumber":"","nonDraftVersions":[{"code":4,"date":"2023-09-05 17:47:29","doi":"10.21203/rs.3.rs-2676239/v4","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}},{"code":3,"date":"2023-09-01 18:38:48","doi":"10.21203/rs.3.rs-2676239/v3","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}},{"code":2,"date":"2023-07-20 15:01:49","doi":"10.21203/rs.3.rs-2676239/v2","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}},{"code":1,"date":"2023-04-06 17:06:52","doi":"10.21203/rs.3.rs-2676239/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":"87042b17-2539-448c-ad26-e3eb108c75c6","owner":[],"postedDate":"September 5th, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":24398963,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2023-04-06T17:06:52+00:00","versionOfRecord":[],"versionCreatedAt":"2023-09-05 17:47:29","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v4","identity":"rs-2676239","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-2676239","identity":"rs-2676239","version":["v4"]},"buildId":"WrCJVZZCHTDjtuVLN7oU0","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}