Triaffine Decoder for span-based Chinese Named Entity Recognition | 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 Triaffine Decoder for span-based Chinese Named Entity Recognition Dongsheng Liu, Qirui Li, Zhiping Peng, Jieguang He, Zhushen Liang, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4460073/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 In recent years, some advanced NER (Named Entity Recognition) models have achieved satisfactory results, but modern neural networks are often plagued by the over-confidence problem. Driven by the lack of entity information in the span-based NER model, we perform lexical enhancement operations for Chinese in the decoding layer of the span-based NER model. Roughly speaking, our model builds on the advanced span-based NER model by utilizing the Triaffine structure to construct a tree-shaped scoring mechanism for the decoding process of entities, and at the same time adding a softlexicon embedding in the input layer of the model. The improved model can introduce more entity information, obtain more advanced performance than before, and alleviate the over-confidence problem. Our model experiments on four well-known Chinese NER datasets and the F1 values on three of them achieve competitive results compared to the baseline model. Chinese Named Entity Recognition Over-confidence Triaffne Decoder Softlexicon 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-4460073","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":305468875,"identity":"1489676e-7a9a-4488-b67d-0ac36c07e306","order_by":0,"name":"Dongsheng Liu","email":"","orcid":"","institution":"Guangdong University of Petrochemical Technology","correspondingAuthor":false,"prefix":"","firstName":"Dongsheng","middleName":"","lastName":"Liu","suffix":""},{"id":305468876,"identity":"c19336b1-5438-408a-a91a-47da31a0a545","order_by":1,"name":"Qirui Li","email":"","orcid":"","institution":"Guangdong University of Petrochemical Technology","correspondingAuthor":false,"prefix":"","firstName":"Qirui","middleName":"","lastName":"Li","suffix":""},{"id":305468877,"identity":"afaf9cf5-9ee1-4604-b1bd-f8c04637d875","order_by":2,"name":"Zhiping Peng","email":"","orcid":"","institution":"Guangdong University of Petrochemical Technology","correspondingAuthor":false,"prefix":"","firstName":"Zhiping","middleName":"","lastName":"Peng","suffix":""},{"id":305468879,"identity":"c60e7a2b-bac6-4389-9c5b-bc5d48b9b29c","order_by":3,"name":"Jieguang He","email":"","orcid":"","institution":"Guangdong University of Petrochemical Technology","correspondingAuthor":false,"prefix":"","firstName":"Jieguang","middleName":"","lastName":"He","suffix":""},{"id":305468882,"identity":"f1c99355-3cc3-4969-a198-c961266f8cba","order_by":4,"name":"Zhushen Liang","email":"","orcid":"","institution":"Guangdong University of Petrochemical Technology","correspondingAuthor":false,"prefix":"","firstName":"Zhushen","middleName":"","lastName":"Liang","suffix":""},{"id":305468886,"identity":"62bf21fa-fd98-43d2-9a40-c7891c11d2bf","order_by":5,"name":"Jinbo Qiu","email":"","orcid":"","institution":"Guangdong University of Petrochemical Technology","correspondingAuthor":false,"prefix":"","firstName":"Jinbo","middleName":"","lastName":"Qiu","suffix":""},{"id":305468888,"identity":"c58282b3-cf79-4303-820f-6d36edc81422","order_by":6,"name":"Delong Cui","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA9ElEQVRIiWNgGAWjYDCCA8wNYJqNvYFBAiKUQEgLI1QLzwGQFgMStDBIJBCphe94Y+Pjgl92iX2Szy/e5t3xh4GfPceA4ecO3FokzxxsNp7Zl5zYJp1TbM17xoBBsueNAWPvGdxaDG4AFfP2HABpSZPmbTMAiuQYMDO24dFy/yFUi+QZiBZ7glpuMLZJ8/wAapFgPwaxRYKAFskzic3GvA3Jxm08OcyWc88Y80iceVZwsBePFr7jhw8+5vljJzu//fjDG293yMnxtydvfPATjxYwgDiDx4ABGEc8IOYBAhqA4A+IYH/AAIvWUTAKRsEoGAXIAAD1rFNe36UfdgAAAABJRU5ErkJggg==","orcid":"","institution":"Guangdong University of Petrochemical Technology","correspondingAuthor":true,"prefix":"","firstName":"Delong","middleName":"","lastName":"Cui","suffix":""}],"badges":[],"createdAt":"2024-05-22 10:07:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4460073/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4460073/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":57718849,"identity":"c7f2afb9-52da-4be3-b3fc-946adec7b5c7","added_by":"auto","created_at":"2024-06-04 18:10:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":638592,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4460073/v1_covered_660f5ccf-8292-4cab-9a5c-1af3fa0ca812.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Triaffine Decoder for span-based Chinese Named Entity Recognition","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":"Chinese Named Entity Recognition, Over-confidence, Triaffne Decoder, Softlexicon","lastPublishedDoi":"10.21203/rs.3.rs-4460073/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4460073/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"In recent years, some advanced NER (Named Entity Recognition) models have achieved satisfactory results, but modern neural networks are often plagued by the over-confidence problem. Driven by the lack of entity information in the span-based NER model, we perform lexical enhancement operations for Chinese in the decoding layer of the span-based NER model. Roughly speaking, our model builds on the advanced span-based NER model by utilizing the Triaffine structure to construct a tree-shaped scoring mechanism for the decoding process of entities, and at the same time adding a softlexicon embedding in the input layer of the model. The improved model can introduce more entity information, obtain more advanced performance than before, and alleviate the over-confidence problem. Our model experiments on four well-known Chinese NER datasets and the F1 values on three of them achieve competitive results compared to the baseline model.","manuscriptTitle":"Triaffine Decoder for span-based Chinese Named Entity Recognition","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-06-04 17:54:18","doi":"10.21203/rs.3.rs-4460073/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":"353e8175-3f66-4758-8392-bbc4779277de","owner":[],"postedDate":"June 4th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-06-04T17:54:21+00:00","versionOfRecord":[],"versionCreatedAt":"2024-06-04 17:54:18","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4460073","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4460073","identity":"rs-4460073","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}
Text is read by the "Ask this paper" AI Q&A widget below.
Extraction quality varies by source — PMC NXML preserves structure
cleanly, OA-HTML may include some navigation residue, and OA-PDF can
have broken hyphenation. The publisher copy
(via DOI)
is the canonical version.