Enhancing Person-Centric Relation Extraction through Multi-Task Learning

Enhancing Person-Centric Relation Extraction through Multi-Task Learning | 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 Person-Centric Relation Extraction through Multi-Task Learning Hailin Wang, Wentong Niu, Hangyi Ren, Jiahao Li, Jingxuan Tian, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6904071/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 Relation extraction (RE) plays a vital role in understanding structured knowledge from text. Despite the prevalence and importance of person-centric relationships in real-world applications, they remain underexplored in current research. Existing models often struggle to capture the implicit semantic cues associated with person entities, resulting in suboptimal performance on such relations. To address this limitation, we propose a novel multi-task learning framework, SELF, designed to enhance extraction performance for person-centric relationships. Specifically, SELF introduces an auxiliary task that explicitly models the semantic space of person-related entities, enabling the model to effectively capture crucial yet sparse semantic information inherent in person-centric contexts. Additionally, SELF incorporates a hierarchical entity fusion module with a multi-layer routing mechanism to adaptively integrate shallow and deep semantic representations, further enriching the model's understanding of person-centric relationships. Extensive experiments conducted on the TACRED dataset, which is rich in person-centric relationships, along with two auxiliary datasets, demonstrate that SELF significantly outperforms existing models in classifying person-centric relations. Person-Centric Relation Extraction Multi-Task Learning Sparse Entity Label Attention Mechanism 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-6904071","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":483697690,"identity":"aa63f505-961f-4871-8900-8f3187cfeb09","order_by":0,"name":"Hailin Wang","email":"","orcid":"","institution":"Southwestern University of Finance and Economics","correspondingAuthor":false,"prefix":"","firstName":"Hailin","middleName":"","lastName":"Wang","suffix":""},{"id":483697691,"identity":"e1a57b35-fedf-48a0-9dcb-c4c061be8546","order_by":1,"name":"Wentong Niu","email":"","orcid":"","institution":"Southwestern University of Finance and Economics","correspondingAuthor":false,"prefix":"","firstName":"Wentong","middleName":"","lastName":"Niu","suffix":""},{"id":483697693,"identity":"30d694b3-01f6-4077-9384-ec10197556fc","order_by":2,"name":"Hangyi Ren","email":"","orcid":"","institution":"Southwestern University of Finance and Economics","correspondingAuthor":false,"prefix":"","firstName":"Hangyi","middleName":"","lastName":"Ren","suffix":""},{"id":483697694,"identity":"0f8ee12d-4b99-49bb-a2c0-bc42143ca437","order_by":3,"name":"Jiahao Li","email":"","orcid":"","institution":"Southwestern University of Finance and Economics","correspondingAuthor":false,"prefix":"","firstName":"Jiahao","middleName":"","lastName":"Li","suffix":""},{"id":483697695,"identity":"cec4a3ea-11e8-4917-8873-a67f75cbebce","order_by":4,"name":"Jingxuan Tian","email":"","orcid":"","institution":"Southwestern University of Finance and Economics","correspondingAuthor":false,"prefix":"","firstName":"Jingxuan","middleName":"","lastName":"Tian","suffix":""},{"id":483697696,"identity":"54cb0af8-77e4-4b49-92fb-24dc387e5b25","order_by":5,"name":"Dan Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA70lEQVRIie3LMYvCMBTA8ScFp7auKQX9CpGA3CD6VVKy9u4cHQQLgqOu+i0ODjpHAnWJdH2Dyy03uUjgRrnKnWtaN8H8Ie/BIz8Al+sRkwDedXeuY/p/aUairBr6LkJlUxLuD8pMZsfRZ6kHRE6hGyJvmYmFRPqNs03xLXJMK6KBRci9eGMhVKZU+G0lBhjk8XkJyQfytufbSHmiyr8owdaHnOwuMK8nmPYXwVKNKLxWJANO60iEJ+YFK8UJvpsXWZD+Vn8tYhsJy5QZ/0eNO+siQTkb9sK92BkbuZVkf5tUr5U1AADjRr9cLpfrOfsFnolUDCQ7RKgAAAAASUVORK5CYII=","orcid":"","institution":"Southwestern University of Finance and Economics","correspondingAuthor":true,"prefix":"","firstName":"Dan","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2025-06-16 09:38:23","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6904071/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6904071/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":88017209,"identity":"67d86ced-52f1-49e4-b68f-b9a27a0ad6c0","added_by":"auto","created_at":"2025-07-31 13:17:14","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2720821,"visible":true,"origin":"","legend":"","description":"","filename":"supercomputingpersoncentric.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6904071/v1_covered_6ef95a2f-70e4-4067-9bea-adcf825471f3.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Enhancing Person-Centric Relation Extraction through Multi-Task Learning","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":"Person-Centric Relation Extraction, Multi-Task Learning, Sparse Entity Label, Attention Mechanism","lastPublishedDoi":"10.21203/rs.3.rs-6904071/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6904071/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eRelation extraction (RE) plays a vital role in understanding structured knowledge from text. Despite the prevalence and importance of person-centric relationships in real-world applications, they remain underexplored in current research. Existing models often struggle to capture the implicit semantic cues associated with person entities, resulting in suboptimal performance on such relations. To address this limitation, we propose a novel multi-task learning framework, SELF, designed to enhance extraction performance for person-centric relationships. Specifically, SELF introduces an auxiliary task that explicitly models the semantic space of person-related entities, enabling the model to effectively capture crucial yet sparse semantic information inherent in person-centric contexts. Additionally, SELF incorporates a hierarchical entity fusion module with a multi-layer routing mechanism to adaptively integrate shallow and deep semantic representations, further enriching the model's understanding of person-centric relationships. Extensive experiments conducted on the TACRED dataset, which is rich in person-centric relationships, along with two auxiliary datasets, demonstrate that SELF significantly outperforms existing models in classifying person-centric relations.\u003c/p\u003e","manuscriptTitle":"Enhancing Person-Centric Relation Extraction through Multi-Task Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-11 17:26:55","doi":"10.21203/rs.3.rs-6904071/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":"cf6b40a7-dd7f-4cc7-9f7e-8ad9c6202bd7","owner":[],"postedDate":"July 11th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-07-31T13:09:02+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-11 17:26:55","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6904071","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6904071","identity":"rs-6904071","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}