Automatic summarization model based on clustering algorithm

Automatic summarization model based on clustering algorithm | 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PDF Article Automatic summarization model based on clustering algorithm Wenzhuo Dai, Qing He This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3992927/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 Extractive document summary (EDS) is usually seen as a sequence labeling task, which the summary is formulated by sentences from the original document. However, the selected sentences usually are high redundancy in semantic space, so that the composed summary are high semantic redundancy. To alleviate this problem, we propose a model to reduce the semantic redundancy of summary by introducing the cluster algorithm in semantic space. We evaluate our model and perform significance testing on the CNN/DailyMail datasets compare with baselines. Physical sciences/Mathematics and computing/Computer science Physical sciences/Mathematics and computing/Information technology EDS Cluster Algorithm Semantic Space Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 05 Jun, 2024 Reviews received at journal 03 Jun, 2024 Reviews received at journal 25 May, 2024 Reviewers agreed at journal 21 May, 2024 Reviewers agreed at journal 02 May, 2024 Reviewers invited by journal 02 May, 2024 Editor assigned by journal 30 Apr, 2024 Editor invited by journal 17 Mar, 2024 Submission checks completed at journal 17 Mar, 2024 First submitted to journal 26 Feb, 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-3992927","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":281003648,"identity":"0cddd95d-3220-45a9-95bb-141dfd1a201d","order_by":0,"name":"Wenzhuo Dai","email":"","orcid":"","institution":"Guizhou University","correspondingAuthor":false,"prefix":"","firstName":"Wenzhuo","middleName":"","lastName":"Dai","suffix":""},{"id":281003649,"identity":"36fe3e3b-afe3-4d26-b0d6-76c9adcd6e54","order_by":1,"name":"Qing He","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAArElEQVRIiWNgGAWjYDACCQbGBxBWAvFamA1I1sImQZoWvtvNxyq//DnMwM+eY8DwcwcRWiTvHEu7LcNzmEGy540BY+8ZIrQY3Mgxuy0hcRjEMGBmbCNKS/63YgmDwwz2JGjJYWP8kAC0RYJYLZI30oylGQ6k80iceVZwsJcYLXw3kh9+/PHHWo6/PXnjg5/EaGE4wMDAzMPAwANlE6mF8QdxSkfBKBgFo2CkAgCB7TXTsNMS/gAAAABJRU5ErkJggg==","orcid":"","institution":"Guizhou University","correspondingAuthor":true,"prefix":"","firstName":"Qing","middleName":"","lastName":"He","suffix":""}],"badges":[],"createdAt":"2024-02-27 05:29:38","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3992927/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3992927/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":53105566,"identity":"334894a2-b138-41d3-81b3-1dba0a1ee647","added_by":"auto","created_at":"2024-03-20 16:06:59","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":372669,"visible":true,"origin":"","legend":"","description":"","filename":"Automaticsummarizationmodelbasedonclusteringalgorithm.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3992927/v1_covered_f6d7e318-d08a-4649-8937-390a0c463426.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eAutomatic summarization model based on clustering algorithm\u003c/p\u003e","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"EDS, Cluster Algorithm, Semantic Space","lastPublishedDoi":"10.21203/rs.3.rs-3992927/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3992927/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eExtractive document summary (EDS) is usually seen as a sequence labeling task, which the summary is formulated by sentences from the original document. However, the selected sentences usually are high redundancy in semantic space, so that the composed summary are high semantic redundancy. To alleviate this problem, we propose a model to reduce the semantic redundancy of summary by introducing the cluster algorithm in semantic space. We evaluate our model and perform significance testing on the CNN/DailyMail datasets compare with baselines.\u003c/p\u003e","manuscriptTitle":"Automatic summarization model based on clustering algorithm","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-03-20 15:58:51","doi":"10.21203/rs.3.rs-3992927/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-06-05T11:28:12+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-06-03T04:00:34+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-05-25T04:26:56+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"62076148133701509162473641577615576017","date":"2024-05-21T12:33:57+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"7af806ba-023d-4edc-ba0d-e02b6cda2c17","date":"2024-05-02T14:22:15+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-05-02T13:49:53+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-04-30T06:20:42+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2024-03-17T09:36:45+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-03-17T08:31:17+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2024-02-27T04:56:28+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"8772a53a-f25d-4696-a490-c79f47e71410","owner":[],"postedDate":"March 20th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":29682794,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":29682795,"name":"Physical sciences/Mathematics and computing/Information technology"}],"tags":[],"updatedAt":"2024-07-01T05:16:24+00:00","versionOfRecord":[],"versionCreatedAt":"2024-03-20 15:58:51","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3992927","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3992927","identity":"rs-3992927","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}