TMSFE: A Transformer-Based Multi-Label Semantic Feature Extraction Method

TMSFE: A Transformer-Based Multi-Label Semantic Feature Extraction Method | 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 TMSFE: A Transformer-Based Multi-Label Semantic Feature Extraction Method Liqun Xiao, Jiashu Zhang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7656449/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 03 Dec, 2025 Read the published version in Scientific Reports → Version 1 posted 10 You are reading this latest preprint version Abstract Multi-label text classification is a critical task in natural language processing, in which each document may belong to multiple categories. This setting is challenging, as it involves complex label dependencies and requires extracting fine-grained semantic features for each label. We propose a novel Transformer-based algorithm, TMSFE Transformer-based multi-label semantic feature extraction, which integrates label-specific query embeddings with a multi-head attention mechanism to extract discriminative features for each potential label and leverages a Latent semantic space to enhance the efficiency of feature extraction. Unlike conventional single-label classifiers or flat multi-label methods, the proposed model designs a DeBERTaV3-based Transformer encoder to jointly model the document and label semantics. Additionally, the proposed SimCSE-Based latent semantic space module projects text and label representations into a shared latent semantic space to enhance feature extraction efficiency. And a sigmoid-based multi-label classification head is applied to the extracted features. Results show that the proposed TMSFE consistently outperforms baseline models, achieving lower Hamming loss and higher feature extraction accuracy. Biological sciences/Computational biology and bioinformatics Physical sciences/Engineering Physical sciences/Mathematics and computing Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 03 Dec, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 13 Oct, 2025 Reviews received at journal 07 Oct, 2025 Reviews received at journal 02 Oct, 2025 Reviewers agreed at journal 01 Oct, 2025 Reviewers agreed at journal 30 Sep, 2025 Reviewers invited by journal 30 Sep, 2025 Editor assigned by journal 30 Sep, 2025 Editor invited by journal 25 Sep, 2025 Submission checks completed at journal 24 Sep, 2025 First submitted to journal 24 Sep, 2025 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-7656449","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":527694158,"identity":"25bfefa1-3641-4b59-985d-d168ccfb41c7","order_by":0,"name":"Liqun Xiao","email":"","orcid":"","institution":"Southwest Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Liqun","middleName":"","lastName":"Xiao","suffix":""},{"id":527694159,"identity":"926c2548-275b-46a7-a74a-5f9911b58fae","order_by":1,"name":"Jiashu Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABE0lEQVRIiWNgGAWjYBACxgYGNhAtZwAVYAaTPERoMYZr4SGkBQjAWhI3wLgEtTD3H3/24OeO2vTt7N2JDxj+HGa3l0hgfPC2jUHeHJfDZiSkG/aeOZ67s+fsZgPGtsPMPBIJzIZz2xgMdzbg0sJwTIK37Vjuhhu52yQYG26DtLBJ87YxJBgcwKGl/2Cb5N+2Y+kGN3K3/2D4A9bC/huvloZkkJk1CUAt24BBAbGFGa+WGWls0rJtBww3nDm7WSKx7T8zz5mHzZJzzkkYbsChxRAYYpJv2+rkDY73bvzw4U9aMnt78sEPb8ps5HHZYggJlsMQXgIDQzI4ehkYJLCrBwJ5CFUHF7DDqXQUjIJRMApGLAAAuqJbl/Oz4q8AAAAASUVORK5CYII=","orcid":"","institution":"Southwest Jiaotong University","correspondingAuthor":true,"prefix":"","firstName":"Jiashu","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2025-09-19 08:53:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7656449/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7656449/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-30925-2","type":"published","date":"2025-12-03T15:57:57+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":93358898,"identity":"e56bce96-5cde-4d11-94d8-e321d4043c1a","added_by":"auto","created_at":"2025-10-13 02:24:45","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4108,"visible":true,"origin":"","legend":"","description":"","filename":"3465cb61783b43de872175980e33b41b.json","url":"https://assets-eu.researchsquare.com/files/rs-7656449/v1/61b7991b9a80f9b79b26434e.json"},{"id":97724593,"identity":"f22eedd4-a192-40ec-8527-d803e2f5cea8","added_by":"auto","created_at":"2025-12-08 16:12:49","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":387100,"visible":true,"origin":"","legend":"","description":"","filename":"TMSEF.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7656449/v1_covered_b96800eb-1bc2-4c6f-843b-b21219df12fa.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"TMSFE: A Transformer-Based Multi-Label Semantic Feature Extraction Method","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":"","lastPublishedDoi":"10.21203/rs.3.rs-7656449/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7656449/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Multi-label text classification is a critical task in natural language processing, in which each document may belong to multiple categories. This setting is challenging, as it involves complex label dependencies and requires extracting fine-grained semantic features for each label. We propose a novel Transformer-based algorithm, TMSFE Transformer-based multi-label semantic feature extraction, which integrates label-specific query embeddings with a multi-head attention mechanism to extract discriminative features for each potential label and leverages a Latent semantic space to enhance the efficiency of feature extraction. Unlike conventional single-label classifiers or flat multi-label methods, the proposed model designs a DeBERTaV3-based Transformer encoder to jointly model the document and label semantics. Additionally, the proposed SimCSE-Based latent semantic space module projects text and label representations into a shared latent semantic space to enhance feature extraction efficiency. And a sigmoid-based multi-label classification head is applied to the extracted features. Results show that the proposed TMSFE consistently outperforms baseline models, achieving lower Hamming loss and higher feature extraction accuracy.","manuscriptTitle":"TMSFE: A Transformer-Based Multi-Label Semantic Feature Extraction Method","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-13 02:24:41","doi":"10.21203/rs.3.rs-7656449/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-10-13T10:46:34+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-07T13:42:42+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-02T08:25:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"8226570015084467128393748906502413493","date":"2025-10-01T04:54:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"270171260742245788635365432040624655578","date":"2025-09-30T15:02:09+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-30T13:07:54+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-30T13:06:24+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-09-25T17:51:17+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-25T02:38:57+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-09-25T02:37:28+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":"1cb12ff4-42b5-43eb-bd9f-81e9df72bed5","owner":[],"postedDate":"October 13th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":56093514,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":56093515,"name":"Physical sciences/Engineering"},{"id":56093516,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2025-12-08T16:09:32+00:00","versionOfRecord":{"articleIdentity":"rs-7656449","link":"https://doi.org/10.1038/s41598-025-30925-2","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-12-03 15:57:57","publishedOnDateReadable":"December 3rd, 2025"},"versionCreatedAt":"2025-10-13 02:24:41","video":"","vorDoi":"10.1038/s41598-025-30925-2","vorDoiUrl":"https://doi.org/10.1038/s41598-025-30925-2","workflowStages":[]},"version":"v1","identity":"rs-7656449","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7656449","identity":"rs-7656449","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}