Document-level causal event extraction enhanced by temporal relation using dual-channel neural network

Document-level causal event extraction enhanced by temporal relation using dual-channel neural network | 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 Article Document-level causal event extraction enhanced by temporal relation using dual-channel neural network Zishu Liu, Yongquan Liang, Weijian Ni This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5802602/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 Event-event causal relation extraction (ECRE) represents a critical yet challenging task in natural language processing. Existing studies primarily focus on extracting causal sentences and events, despite the use of joint extraction methods for both tasks. However, both pipeline methods and joint extraction approaches often overlook the impact of document-level event temporal sequences on causal relationships. To address this limitation, we propose a model that incorporates document-level event temporal order information to enhance the extraction of implicit event causal relations. The proposed model comprises two channels: Event-event causal relation extraction channel (ECC) and event-event temporal relation extraction channel (ETC). Temporal features provide critical support for modeling node weights in the causal graph, thereby improving the accuracy of causal reasoning. Association link network (ALN) is introduced to construct event causality graph (ECG), incorporating an innovative design that computes node weights using Kullback-Leibler divergence and Gaussian kernels. Experimental results indicate that our model significantly outperforms baseline models in terms of accuracy and weighted average F1 scores. Physical sciences/Materials science Physical sciences/Mathematics and computing Event-event causal relation extraction Event-event temporal relation extraction Document-level causality Graph convolutional network 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-5802602","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":401517384,"identity":"1106f9d3-56cc-40fe-867c-8bf1c004e104","order_by":0,"name":"Zishu Liu","email":"","orcid":"","institution":"Shandong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Zishu","middleName":"","lastName":"Liu","suffix":""},{"id":401517385,"identity":"5949bfd5-b1b3-4f3e-a923-09134846fd9e","order_by":1,"name":"Yongquan Liang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAu0lEQVRIiWNgGAWjYBACPgYGxgcMbBCOBFFagIqZDUAkDyla2CRI1CKRvK3yR9lhe3sG5oO3eRjs8ojQklZ2m+fc4cQeBrZkax6G5GIitOSY3WZsO5zAw8BjJs3DcCCxgRgthT/bDtvzMPB/I14LA2/bYcYeBh42IrXwPCuW5jmXnthzmM3Yco5BMmEt/OzJGz/+KLO2Z29vfnjjTYUdYS0MAgkGEAYziDAgqB5kzQGilI2CUTAKRsFIBgAaSjDY6sujZgAAAABJRU5ErkJggg==","orcid":"","institution":"Shandong University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Yongquan","middleName":"","lastName":"Liang","suffix":""},{"id":401517387,"identity":"8b77e85d-5402-4d47-a0f9-ee39af1e3b89","order_by":2,"name":"Weijian Ni","email":"","orcid":"","institution":"Shandong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Weijian","middleName":"","lastName":"Ni","suffix":""}],"badges":[],"createdAt":"2025-01-10 09:53:31","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5802602/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5802602/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":77765019,"identity":"695a43cd-d868-4cdf-ba2b-27a92c025545","added_by":"auto","created_at":"2025-03-05 09:54:12","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1449759,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5802602/v1_covered_a3852280-59a9-46e1-ba2a-dd13c7504f55.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Document-level causal event extraction enhanced by temporal relation using dual-channel neural network","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":"Event-event causal relation extraction, Event-event temporal relation extraction, Document-level causality, Graph convolutional network","lastPublishedDoi":"10.21203/rs.3.rs-5802602/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5802602/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eEvent-event causal relation extraction (ECRE) represents a critical yet challenging task in natural language processing. Existing studies primarily focus on extracting causal sentences and events, despite the use of joint extraction methods for both tasks. However, both pipeline methods and joint extraction approaches often overlook the impact of document-level event temporal sequences on causal relationships. To address this limitation, we propose a model that incorporates document-level event temporal order information to enhance the extraction of implicit event causal relations. The proposed model comprises two channels: Event-event causal relation extraction channel (ECC) and event-event temporal relation extraction channel (ETC). Temporal features provide critical support for modeling node weights in the causal graph, thereby improving the accuracy of causal reasoning. Association link network (ALN) is introduced to construct event causality graph (ECG), incorporating an innovative design that computes node weights using Kullback-Leibler divergence and Gaussian kernels. Experimental results indicate that our model significantly outperforms baseline models in terms of accuracy and weighted average F1 scores.\u003c/p\u003e","manuscriptTitle":"Document-level causal event extraction enhanced by temporal relation using dual-channel neural network","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-01-15 09:57:37","doi":"10.21203/rs.3.rs-5802602/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":"3bce50a5-c1cf-44fb-9c4e-a2e016317150","owner":[],"postedDate":"January 15th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":42790006,"name":"Physical sciences/Materials science"},{"id":42790007,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2025-03-05T09:53:44+00:00","versionOfRecord":[],"versionCreatedAt":"2025-01-15 09:57:37","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5802602","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5802602","identity":"rs-5802602","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}