DEIB: A Dual-stage Enhanced Information Bottleneck Framework for Joint Entity and Relation Extraction

DEIB: A Dual-stage Enhanced Information Bottleneck Framework for Joint Entity and Relation 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 DEIB: A Dual-stage Enhanced Information Bottleneck Framework for Joint Entity and Relation Extraction Xiaoyong Liu, Wuquan Lin, Miao Hu, Chunlin Xu, Huihui Li This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9084876/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 10 You are reading this latest preprint version Abstract Joint Entity and Relation Extraction (JERE) aims to simultaneously identify entities and their semantic relations. Despite substantial progress, current JERE models are still hindered by redundant contextual information and noise introduced by external knowledge, which obscure the sparse scientific semantics embedded in biomedical texts, while semantic inconsistencies between entity recognition and relation extraction further weaken the coherence of joint reasoning. To mitigate these limitations, we propose a Dual-stage Enhanced Information Bottleneck (DEIB) framework. DEIB incorporates dual-stage IB modules that progressively compress span-level and knowledge-enhanced representations, thereby filtering task-irrelevant contextual signals and suppressing noise arising from imperfect external knowledge. In addition, a Semantic-Consistent Interaction Module (SCIM) is designed to alleviate cross-subtask semantic inconsistency by reformulating the traditional biaffine scorer into a cross-task reasoning layer that captures high-order dependencies between entity and relation representations. Through ablation studies and case analyses, we confirm that each component of the DEIB framework is critical to improving robustness, as they collectively suppress redundant context and knowledge noise while enhancing cross-subtask semantic consistency. Furthermore, comparative experiments on the BioRelEx and ADE datasets show that DEIB achieves state-of-the-art results, with F1-scores of 93.42% and 79.85% for entity and relation extraction on BioRelEx, and 93.31% and 87.26% on ADE. These experimental results validate that DEIB is accurate and effective. Joint Entity and Relation Extraction Dual-stage Enhanced Information Bottleneck Semantic-Consistent Interaction Module External Knowledge Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 05 May, 2026 Reviews received at journal 03 May, 2026 Reviewers agreed at journal 09 Apr, 2026 Reviewers agreed at journal 07 Apr, 2026 Reviews received at journal 23 Mar, 2026 Reviewers agreed at journal 23 Mar, 2026 Reviewers invited by journal 19 Mar, 2026 Editor assigned by journal 15 Mar, 2026 Submission checks completed at journal 12 Mar, 2026 First submitted to journal 10 Mar, 2026 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-9084876","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":610357249,"identity":"a2bdec45-94b3-4060-94f9-be62b8cbefe3","order_by":0,"name":"Xiaoyong Liu","email":"","orcid":"","institution":"Guangdong Polytechnic Normal University","correspondingAuthor":false,"prefix":"","firstName":"Xiaoyong","middleName":"","lastName":"Liu","suffix":""},{"id":610357250,"identity":"4d3c2196-7276-4cc3-bad6-d3c609d2c017","order_by":1,"name":"Wuquan Lin","email":"","orcid":"","institution":"Guangdong Polytechnic Normal University","correspondingAuthor":false,"prefix":"","firstName":"Wuquan","middleName":"","lastName":"Lin","suffix":""},{"id":610357251,"identity":"90c238a4-5dcb-43f8-9f9f-21b2cbd250cc","order_by":2,"name":"Miao Hu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAx0lEQVRIiWNgGAWjYBACAyA+wMBgA+WyEa8ljUQtQHCYBC3mEtmJB35UnLfbLt1jwPCh7DAD/+wG/FosZ+RuONhz5nbyzjlnDBhnnDvMIHHnAAGH3cjdcIC37XaywY0cA2betsMMBhIJhLUc/Nt2DqLlL7FaDvO2HbADa2EkSsuZtxsOy5xJTrCckVZwsOdcOo/EDUJajudu/vimws7eXCJ544MfZdZy/DMIaIGBxA0M4Dhl4CFOPRDYGxCtdBSMglEwCkYcAABY7EmjMUawVAAAAABJRU5ErkJggg==","orcid":"","institution":"Guangdong Polytechnic Normal University","correspondingAuthor":true,"prefix":"","firstName":"Miao","middleName":"","lastName":"Hu","suffix":""},{"id":610357252,"identity":"abd6ff16-e14c-4058-b93c-bfba7a0e6876","order_by":3,"name":"Chunlin Xu","email":"","orcid":"","institution":"Guangdong Polytechnic Normal University","correspondingAuthor":false,"prefix":"","firstName":"Chunlin","middleName":"","lastName":"Xu","suffix":""},{"id":610357254,"identity":"6b224341-1896-4f02-b09b-7e7284f5912b","order_by":4,"name":"Huihui Li","email":"","orcid":"","institution":"Guangdong Polytechnic Normal University","correspondingAuthor":false,"prefix":"","firstName":"Huihui","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2026-03-10 13:56:30","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9084876/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9084876/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105307417,"identity":"010710d5-dccd-4e33-a22c-13970c6129ca","added_by":"auto","created_at":"2026-03-24 14:50:21","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1177647,"visible":true,"origin":"","legend":"","description":"","filename":"DEIB.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9084876/v1_covered_3c5794dd-d310-412c-ad20-c1740ddd2d69.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"DEIB: A Dual-stage Enhanced Information Bottleneck Framework for Joint Entity and Relation Extraction ","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"international-journal-of-machine-learning-and-cybernetics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jmlc","sideBox":"Learn more about [International Journal of Machine Learning and Cybernetics](http://actavetscand.biomedcentral.com/)","snPcode":"13042","submissionUrl":"https://submission.nature.com/new-submission/13042/3","title":"International Journal of Machine Learning and Cybernetics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Joint Entity and Relation Extraction, Dual-stage Enhanced Information Bottleneck, Semantic-Consistent Interaction Module, External Knowledge","lastPublishedDoi":"10.21203/rs.3.rs-9084876/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9084876/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eJoint Entity and Relation Extraction (JERE) aims to simultaneously identify entities and their semantic relations. Despite substantial progress, current JERE models are still hindered by redundant contextual information and noise introduced by external knowledge, which obscure the sparse scientific semantics embedded in biomedical texts, while semantic inconsistencies between entity recognition and relation extraction further weaken the coherence of joint reasoning. To mitigate these limitations, we propose a Dual-stage Enhanced Information Bottleneck (DEIB) framework. DEIB incorporates dual-stage IB modules that progressively compress span-level and knowledge-enhanced representations, thereby filtering task-irrelevant contextual signals and suppressing noise arising from imperfect external knowledge. In addition, a Semantic-Consistent Interaction Module (SCIM) is designed to alleviate cross-subtask semantic inconsistency by reformulating the traditional biaffine scorer into a cross-task reasoning layer that captures high-order dependencies between entity and relation representations. Through ablation studies and case analyses, we confirm that each component of the DEIB framework is critical to improving robustness, as they collectively suppress redundant context and knowledge noise while enhancing cross-subtask semantic consistency. Furthermore, comparative experiments on the BioRelEx and ADE datasets show that DEIB achieves state-of-the-art results, with F1-scores of 93.42% and 79.85% for entity and relation extraction on BioRelEx, and 93.31% and 87.26% on ADE. These experimental results validate that DEIB is accurate and effective.\u003c/p\u003e","manuscriptTitle":"DEIB: A Dual-stage Enhanced Information Bottleneck Framework for Joint Entity and Relation Extraction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-24 14:50:04","doi":"10.21203/rs.3.rs-9084876/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-05-06T03:34:05+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-03T11:18:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"178368436200053553026107667086115901339","date":"2026-04-09T15:17:52+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"89769066955011393143464713642868488270","date":"2026-04-08T00:55:33+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-24T01:49:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"240751498198641604878017706517332744021","date":"2026-03-23T04:09:17+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-19T23:50:44+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-15T12:21:59+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-13T02:58:31+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal of Machine Learning and Cybernetics","date":"2026-03-10T13:42:46+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"international-journal-of-machine-learning-and-cybernetics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jmlc","sideBox":"Learn more about [International Journal of Machine Learning and Cybernetics](http://actavetscand.biomedcentral.com/)","snPcode":"13042","submissionUrl":"https://submission.nature.com/new-submission/13042/3","title":"International Journal of Machine Learning and Cybernetics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"48d78a34-e1d5-41c4-9514-bfbddc61135b","owner":[],"postedDate":"March 24th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-05-06T03:34:05+00:00","index":64,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-03T11:18:43+00:00","index":63,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-03-24T14:50:04+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-24 14:50:04","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9084876","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9084876","identity":"rs-9084876","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}