CONCORD: Enhancing COVID-19 Research with Weak-Supervision based Numerical Claim Extraction

CONCORD: Enhancing COVID-19 Research with Weak-Supervision based Numerical Claim Extraction | 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 CONCORD: Enhancing COVID-19 Research with Weak-Supervision based Numerical Claim Extraction Dhwanil Shah, Krish Shah, Manan Jagani, Agam Shah, Bhaskar Chaudhury This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4076902/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 17 Sep, 2024 Read the published version in Journal of Intelligent Information Systems → Version 1 posted 9 You are reading this latest preprint version Abstract The COVID-19 Numerical Claims Open Research Dataset (CONCORD) is a comprehensive, open-source dataset that extracts numerical claims from academic papers on COVID-19 research. To extract numerical claims, a weak-supervision based model is employed, leveraging its white-box, explainable nature and advantages over transformer-based models in terms of computational and manual annotation costs. Labelling functions are used to programmatically generate labels, incorporating techniques like pattern matching, external knowledge bases, phrase matching, and third-party models. An aggregator function reconciles overlapping or contradictory labels. The weak-supervision model is evaluated against established baselines and transformer based models, achieving a weighted F1-score of 0.932 and micro F1-score of 0.930 in extracting numerical claims.While the weak-supervision model showcases superior performance compared to baseline models, it is observed that transformer-based models achieve comparable results.CONCORD, comprising around 200,000 numerical claims extracted from over 57,000 COVID-19 research articles, serves as a valuable tool for knowledge discovery and understanding the chronological developments in various research areas associated with COVID-19. In conclusion, CONCORD, alongside the weak-supervision methodology, offers researchers a valuable resource, enhancing advancements in COVID-19 research while highlighting the significant potential of weak-supervision models within the broader biomedical domain. Natural Language Processing Weak-supervision COVID-19 Numerical Claim Detection COVID-19 dataset Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 17 Sep, 2024 Read the published version in Journal of Intelligent Information Systems → Version 1 posted Editorial decision: Revision requested 08 Jul, 2024 Reviews received at journal 27 Jun, 2024 Reviewers agreed at journal 22 May, 2024 Reviews received at journal 18 May, 2024 Reviewers agreed at journal 17 May, 2024 Reviewers invited by journal 25 Mar, 2024 Editor assigned by journal 15 Mar, 2024 Submission checks completed at journal 14 Mar, 2024 First submitted to journal 11 Mar, 2024 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-4076902","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":280181255,"identity":"cf363f2b-da45-4bfe-9ad2-9cb73df4b531","order_by":0,"name":"Dhwanil Shah","email":"","orcid":"","institution":"Dhirubhai Ambani Institute of Information and Communication Technology","correspondingAuthor":false,"prefix":"","firstName":"Dhwanil","middleName":"","lastName":"Shah","suffix":""},{"id":280181258,"identity":"18d57621-4f5c-4c9a-9149-dc4bdc5da6d2","order_by":1,"name":"Krish Shah","email":"","orcid":"","institution":"Dhirubhai Ambani Institute of Information and Communication Technology","correspondingAuthor":false,"prefix":"","firstName":"Krish","middleName":"","lastName":"Shah","suffix":""},{"id":280181259,"identity":"3675d957-deb2-4d6a-b221-2c99f2c42c17","order_by":2,"name":"Manan Jagani","email":"","orcid":"","institution":"Dhirubhai Ambani Institute of Information and Communication Technology","correspondingAuthor":false,"prefix":"","firstName":"Manan","middleName":"","lastName":"Jagani","suffix":""},{"id":280181260,"identity":"b2bf1fdf-4103-40d3-876e-c245426fe9c7","order_by":3,"name":"Agam Shah","email":"","orcid":"","institution":"Georgia Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Agam","middleName":"","lastName":"Shah","suffix":""},{"id":280181261,"identity":"7387965c-9804-4e66-b5db-ee84835633f9","order_by":4,"name":"Bhaskar Chaudhury","email":"data:image/png;base64,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","orcid":"","institution":"Dhirubhai Ambani Institute of Information and Communication Technology","correspondingAuthor":true,"prefix":"","firstName":"Bhaskar","middleName":"","lastName":"Chaudhury","suffix":""}],"badges":[],"createdAt":"2024-03-11 17:15:27","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4076902/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4076902/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s10844-024-00885-6","type":"published","date":"2024-09-17T15:57:52+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":65104062,"identity":"5fee9c03-4e2d-4b1b-8e3e-75c875da927c","added_by":"auto","created_at":"2024-09-23 16:11:23","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2254036,"visible":true,"origin":"","legend":"","description":"","filename":"JournalofIntelligentInformationSystems.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4076902/v1_covered_e0539cb7-542e-432e-a82c-9cb854a08cf4.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"CONCORD: Enhancing COVID-19 Research with Weak-Supervision based Numerical Claim Extraction","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":"journal-of-intelligent-information-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jiis","sideBox":"Learn more about [Journal of Intelligent Information Systems](http://link.springer.com/journal/10844)","snPcode":"10844","submissionUrl":"https://submission.nature.com/new-submission/10844/3","title":"Journal of Intelligent Information Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Natural Language Processing, Weak-supervision, COVID-19, Numerical Claim Detection, COVID-19 dataset","lastPublishedDoi":"10.21203/rs.3.rs-4076902/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4076902/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The COVID-19 Numerical Claims Open Research Dataset (CONCORD) is a comprehensive, open-source dataset that extracts numerical claims from academic papers on COVID-19 research. To extract numerical claims, a weak-supervision based model is employed, leveraging its white-box, explainable nature and advantages over transformer-based models in terms of computational and manual annotation costs. Labelling functions are used to programmatically generate labels, incorporating techniques like pattern matching, external knowledge bases, phrase matching, and third-party models. An aggregator function reconciles overlapping or contradictory labels. The weak-supervision model is evaluated against established baselines and transformer based models, achieving a weighted F1-score of 0.932 and micro F1-score of 0.930 in extracting numerical claims.While the weak-supervision model showcases superior performance compared to baseline models, it is observed that transformer-based models achieve comparable results.CONCORD, comprising around 200,000 numerical claims extracted from over 57,000 COVID-19 research articles, serves as a valuable tool for knowledge discovery and understanding the chronological developments in various research areas associated with COVID-19. In conclusion, CONCORD, alongside the weak-supervision methodology, offers researchers a valuable resource, enhancing advancements in COVID-19 research while highlighting the significant potential of weak-supervision models within the broader biomedical domain.","manuscriptTitle":"CONCORD: Enhancing COVID-19 Research with Weak-Supervision based Numerical Claim Extraction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-03-18 02:44:36","doi":"10.21203/rs.3.rs-4076902/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-07-08T09:45:13+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-06-27T18:08:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"57845458919295202250578111320798659276","date":"2024-05-22T21:17:50+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-05-18T15:24:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"54232366105378070180847643409290550454","date":"2024-05-17T08:21:23+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-03-25T12:37:32+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-03-15T23:56:16+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-03-14T23:41:59+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Intelligent Information Systems","date":"2024-03-11T16:57:21+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-intelligent-information-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jiis","sideBox":"Learn more about [Journal of Intelligent Information Systems](http://link.springer.com/journal/10844)","snPcode":"10844","submissionUrl":"https://submission.nature.com/new-submission/10844/3","title":"Journal of Intelligent Information Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"42b96cfa-666f-47c3-a061-a1d6e09db97e","owner":[],"postedDate":"March 18th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-09-23T16:04:10+00:00","versionOfRecord":{"articleIdentity":"rs-4076902","link":"https://doi.org/10.1007/s10844-024-00885-6","journal":{"identity":"journal-of-intelligent-information-systems","isVorOnly":false,"title":"Journal of Intelligent Information Systems"},"publishedOn":"2024-09-17 15:57:52","publishedOnDateReadable":"September 17th, 2024"},"versionCreatedAt":"2024-03-18 02:44:36","video":"","vorDoi":"10.1007/s10844-024-00885-6","vorDoiUrl":"https://doi.org/10.1007/s10844-024-00885-6","workflowStages":[]},"version":"v1","identity":"rs-4076902","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4076902","identity":"rs-4076902","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}