Data Rescue of Historical Tables Through Semi-Supervised Table Structure Recognition

Data Rescue of Historical Tables Through Semi-Supervised Table Structure Recognition | 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 Data Rescue of Historical Tables Through Semi-Supervised Table Structure Recognition Loitongbam Gyanendro Singh, Stuart E. Middleton This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5842111/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 01 Dec, 2025 Read the published version in International Journal on Document Analysis and Recognition (IJDAR) → Version 1 posted 9 You are reading this latest preprint version Abstract This study uses a novel semi-supervised learning framework to explore Tabular Structure Recognition (TSR) for digitizing historical documents, specifically employing the CascadeTabNet model. TSR is crucial for transforming archival tabular data into digital formats, enhancing accessibility and analysis across various research fields. Challenges like physical degradation, inconsistent lighting, and non-standard handwriting hinder the generation of high-quality annotations of historical documents needed for effective model training. To address these issues, this research explores two research questions: (I) Can a semi-supervised training approach reduce the need for expensive data annotations? and (ii) Does semi-supervised training improve model robustness? We applied our methodology across three datasets: the GloSAT and ICDAR-2019 datasets based on historical documents, and the predominantly modern documents PubTabNet dataset. Our results indicate that semi-supervised learning substantially increases TSR accuracy and decreases dependency on extensive labelled datasets, providing a robust solution for large-scale digitization initiatives and contributing to the preservation and improved accessibility of historical data. All code from this paper is freely available on GitHub. Tabular Structure Recognition Semi-Supervised Learning Historical Document Digitization Data Annotation Techniques Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 01 Dec, 2025 Read the published version in International Journal on Document Analysis and Recognition (IJDAR) → Version 1 posted Editorial decision: Revision requested 14 Jul, 2025 Reviews received at journal 19 May, 2025 Reviews received at journal 16 May, 2025 Reviewers agreed at journal 26 Apr, 2025 Reviewers agreed at journal 25 Apr, 2025 Reviewers invited by journal 25 Apr, 2025 Editor assigned by journal 17 Jan, 2025 Submission checks completed at journal 17 Jan, 2025 First submitted to journal 16 Jan, 2025 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-5842111","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":485392153,"identity":"dfd2bc1f-8e9f-4d21-ad43-2c8e00de4627","order_by":0,"name":"Loitongbam Gyanendro Singh","email":"data:image/png;base64,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","orcid":"","institution":"University of Southampton","correspondingAuthor":true,"prefix":"","firstName":"Loitongbam","middleName":"Gyanendro","lastName":"Singh","suffix":""},{"id":485392154,"identity":"98e5fac5-4fb9-46b0-9091-19a5c2e2a736","order_by":1,"name":"Stuart E. Middleton","email":"","orcid":"","institution":"University of Southampton","correspondingAuthor":false,"prefix":"","firstName":"Stuart","middleName":"E.","lastName":"Middleton","suffix":""}],"badges":[],"createdAt":"2025-01-16 13:08:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5842111/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5842111/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s10032-025-00562-6","type":"published","date":"2025-12-01T15:56:57+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":97723753,"identity":"595bed3e-16a6-4501-9aa1-ff32903c24a5","added_by":"auto","created_at":"2025-12-08 16:02:43","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1844339,"visible":true,"origin":"","legend":"","description":"","filename":"IJDAR2024Final3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5842111/v1_covered_b0a56c7c-884a-44b9-bec0-1fec8bb04f27.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Data Rescue of Historical Tables Through Semi-Supervised Table Structure Recognition","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"international-journal-on-document-analysis-and-recognition-ijdar","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ijda","sideBox":"Learn more about [International Journal on Document Analysis and Recognition (IJDAR)](http://link.springer.com/journal/10032)","snPcode":"10032","submissionUrl":"https://submission.nature.com/new-submission/10032/3","title":"International Journal on Document Analysis and Recognition (IJDAR)","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Tabular Structure Recognition, Semi-Supervised Learning, Historical Document Digitization, Data Annotation Techniques","lastPublishedDoi":"10.21203/rs.3.rs-5842111/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5842111/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis study uses a novel semi-supervised learning framework to explore Tabular Structure Recognition (TSR) for digitizing historical documents, specifically employing the CascadeTabNet model. TSR is crucial for transforming archival tabular data into digital formats, enhancing accessibility and analysis across various research fields. Challenges like physical degradation, inconsistent lighting, and non-standard handwriting hinder the generation of high-quality annotations of historical documents needed for effective model training. To address these issues, this research explores two research questions: (I)\u0026nbsp;Can a semi-supervised training approach reduce the need for expensive data annotations? and (ii) Does semi-supervised training improve model robustness? We applied our methodology across three datasets: the GloSAT and ICDAR-2019 datasets based on historical documents, and the predominantly modern documents PubTabNet dataset. Our results indicate that semi-supervised learning substantially increases TSR accuracy and decreases dependency on extensive labelled datasets, providing a robust solution for large-scale digitization initiatives and contributing to the preservation and improved accessibility of historical data. All code from this paper is freely available on GitHub.\u003c/p\u003e","manuscriptTitle":"Data Rescue of Historical Tables Through Semi-Supervised Table Structure Recognition","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-17 08:19:48","doi":"10.21203/rs.3.rs-5842111/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-07-14T21:51:25+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-19T17:37:22+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-16T16:30:48+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"264479740984619829313448287306808823733","date":"2025-04-26T04:08:20+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"329480163257790036434320147441997377188","date":"2025-04-25T21:57:08+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-04-25T21:04:17+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-01-17T17:26:02+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-01-17T07:04:22+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal on Document Analysis and Recognition (IJDAR)","date":"2025-01-16T12:56:28+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"international-journal-on-document-analysis-and-recognition-ijdar","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ijda","sideBox":"Learn more about [International Journal on Document Analysis and Recognition (IJDAR)](http://link.springer.com/journal/10032)","snPcode":"10032","submissionUrl":"https://submission.nature.com/new-submission/10032/3","title":"International Journal on Document Analysis and Recognition (IJDAR)","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"25a71e44-405d-4142-a219-4ff11ed8e2fc","owner":[],"postedDate":"July 17th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-12-08T15:59:01+00:00","versionOfRecord":{"articleIdentity":"rs-5842111","link":"https://doi.org/10.1007/s10032-025-00562-6","journal":{"identity":"international-journal-on-document-analysis-and-recognition-ijdar","isVorOnly":false,"title":"International Journal on Document Analysis and Recognition (IJDAR)"},"publishedOn":"2025-12-01 15:56:57","publishedOnDateReadable":"December 1st, 2025"},"versionCreatedAt":"2025-07-17 08:19:48","video":"","vorDoi":"10.1007/s10032-025-00562-6","vorDoiUrl":"https://doi.org/10.1007/s10032-025-00562-6","workflowStages":[]},"version":"v1","identity":"rs-5842111","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5842111","identity":"rs-5842111","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}