Optimizing Text-to-SQL Transformations: The Potential of Skeleton Decoupling in SKT-SQL

Optimizing Text-to-SQL Transformations: The Potential of Skeleton Decoupling in SKT-SQL | 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 Optimizing Text-to-SQL Transformations: The Potential of Skeleton Decoupling in SKT-SQL Jiawen Yi, Guo Chen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5318111/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 The Text-to-SQL technology faces significant challenges in converting natural language questions into SQL code, particularly in handling complexities and diversities in multi-domain and high-complexity tasks. To address these issues, this paper proposes a novel framework, SKT-SQL, which effectively decomposes the key steps in Text-to-SQL transformation, such as skeleton generation and schema linking, through multi-decoupling and skeleton prompting strategies, thereby simplifying the entire process. SKT-SQL employs a schema decoupler to filter relevant schema items linked to the natural language questions, reducing the burden on the model during the parsing process. Concurrently, the skeleton generator guides the language model in generating accurate SQL questions using an abstract SQL skeleton representation. This innovative strategy significantly enhances the accuracy of SQL skeleton generation using smaller-scale language models and optimizes the final SQL query generation results. The core contribution of this paper lies in the analysis of the potential of skeleton-based decoupling, demonstrating the advantages of SKT-SQL in improving the accuracy of Text-to-SQL generation, and providing new insights for future Text-to-SQL methods. Experimental validation on the Spider dataset shows that SKT-SQL excels in execution accuracy (EX) and exact-match accuracy (EM), showcasing its robust potential in complex query scenarios. Text-to-SQL Semantic Parsing Natural Language Process Decouple Analysis 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-5318111","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":370684852,"identity":"18d4d071-bc33-4363-a8e2-5a92f04e8d62","order_by":0,"name":"Jiawen Yi","email":"","orcid":"","institution":"Central South University","correspondingAuthor":false,"prefix":"","firstName":"Jiawen","middleName":"","lastName":"Yi","suffix":""},{"id":370684853,"identity":"98d15143-0b11-4efa-8379-3b07a55c12b2","order_by":1,"name":"Guo Chen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAt0lEQVRIiWNgGAWjYJACZiCWYyNZizHpWhIbiFYuH5F88HNBxZ30Pvbmgw8YKu7ZEdRreCMtWXrGmWe5bTzHkg0YzhQnE9YyI8eMmbftcG6bRI6ZBGNbQjJBh0G0/Duczib//vsPorTIS4C0NBxOYJPgYWMAarEjqMWA51myNM+xw4ZtPGnGEglnEhII29IODDGemsPy8u2HH374UJFgT9iWA8i8BGIiSB5dBWFbRsEoGAWjYMQBAICxOC9Wzf8MAAAAAElFTkSuQmCC","orcid":"","institution":"Central South University","correspondingAuthor":true,"prefix":"","firstName":"Guo","middleName":"","lastName":"Chen","suffix":""}],"badges":[],"createdAt":"2024-10-23 10:23:28","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5318111/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5318111/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":71453179,"identity":"4de0b45f-7955-47ce-87ac-0fd240395d39","added_by":"auto","created_at":"2024-12-15 18:01:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":423968,"visible":true,"origin":"","legend":"","description":"","filename":"SKTSQL1020.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5318111/v1_covered_fd85cb8b-4ff8-41f7-975d-77e2ff15b09d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Optimizing Text-to-SQL Transformations: The Potential of Skeleton Decoupling in SKT-SQL","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":"Text-to-SQL, Semantic Parsing, Natural Language Process, Decouple Analysis","lastPublishedDoi":"10.21203/rs.3.rs-5318111/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5318111/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe Text-to-SQL technology faces significant challenges in converting natural language questions into SQL code, particularly in handling complexities and diversities in multi-domain and high-complexity tasks. To address these issues, this paper proposes a novel framework, SKT-SQL, which effectively decomposes the key steps in Text-to-SQL transformation, such as skeleton generation and schema linking, through multi-decoupling and skeleton prompting strategies, thereby simplifying the entire process. SKT-SQL employs a schema decoupler to filter relevant schema items linked to the natural language questions, reducing the burden on the model during the parsing process. Concurrently, the skeleton generator guides the language model in generating accurate SQL questions using an abstract SQL skeleton representation. This innovative strategy significantly enhances the accuracy of SQL skeleton generation using smaller-scale language models and optimizes the final SQL query generation results. The core contribution of this paper lies in the analysis of the potential of skeleton-based decoupling, demonstrating the advantages of SKT-SQL in improving the accuracy of Text-to-SQL generation, and providing new insights for future Text-to-SQL methods. Experimental validation on the Spider dataset shows that SKT-SQL excels in execution accuracy (EX) and exact-match accuracy (EM), showcasing its robust potential in complex query scenarios.\u003c/p\u003e","manuscriptTitle":"Optimizing Text-to-SQL Transformations: The Potential of Skeleton Decoupling in SKT-SQL","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-11-06 05:59:02","doi":"10.21203/rs.3.rs-5318111/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":"cedcaa8e-8b9c-4b62-8952-50bc73e39e9f","owner":[],"postedDate":"November 6th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-12-15T17:53:15+00:00","versionOfRecord":[],"versionCreatedAt":"2024-11-06 05:59:02","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5318111","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5318111","identity":"rs-5318111","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}