Character Semantic-Phonetic Structure Enhance Language Models in Classical Chinese

Character Semantic-Phonetic Structure Enhance Language Models in Classical Chinese | 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 Character Semantic-Phonetic Structure Enhance Language Models in Classical Chinese Bolin Chang, Bin Li, Zhixing Xu, Shiyan Ou This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8179135/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 9 You are reading this latest preprint version Abstract Writing systems, as fundamental media for human knowledge preservation and facilitating sociocultural interaction, embody the cognitive characteristics of diverse cultures. Despite the rapid advancement of artificial intelligence and language modeling, mainstream language models remain focused on word-level representations, neglecting the rich semantic and structural information embedded within individual characters. In this work, we present an attempt to integrate semantic-phonetic structural information into language modeling, leveraging classical Chinese as the underlying representative system. Our semantic-phonetic-aware language model achieves significant performance gains over the baseline on two core Classical Chinese processing tasks: Word Segmentation and Part-of-Speech Tagging, unveiling the critical role of internal character structure in enhancing language models' representation and encoding capabilities. Through extensive evaluation and in-depth analysis, we reveal that the improvement originates from the synergistic interaction between semantic and phonetic components, as well as the sequential organization of the semantic-phonetic structure. We further argue that achieving the optimal balance between these components is crucial for enhancing the expressiveness and generalizability of language representations. Overall, our findings highlight that the internal organization of characters not only reflects deeper structural principles of the writing system but also opens up a new paradigm for advancing language model design. Humanities/Language and linguistics Social science/Language and linguistics Humanities/Literature Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 10 Apr, 2026 Reviewers agreed at journal 05 Apr, 2026 Reviewers agreed at journal 18 Mar, 2026 Reviewers agreed at journal 12 Mar, 2026 Reviewers invited by journal 12 Mar, 2026 Editor invited by journal 11 Mar, 2026 Editor assigned by journal 03 Dec, 2025 Submission checks completed at journal 27 Nov, 2025 First submitted to journal 22 Nov, 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-8179135","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":606301203,"identity":"0f3fa18d-0a0c-41d9-a1fd-0fee0a579391","order_by":0,"name":"Bolin Chang","email":"","orcid":"","institution":"Nanjing University","correspondingAuthor":false,"prefix":"","firstName":"Bolin","middleName":"","lastName":"Chang","suffix":""},{"id":606301204,"identity":"5b1ca82b-1f54-4ae4-9224-48dde17a1f8c","order_by":1,"name":"Bin Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAq0lEQVRIiWNgGAWjYBACPmYexgcMPGC2AXFa2Jh5mA1I1MLAwyYBZROrhZ33WHWBzJ3EBvbmbRIMNXeIcRhf2u0ZPM8SG3iOlUkwHHtGjBYes9s8PIcTGyRyzCQYGw4Tp6UYrEX+DQlamCG28BCthS9ZGqjFuI0nrdgi4RgRWvj5zx78zNtzWLaf/fDGGx9qiNACBow9oAgCggQiNQDBD+KVjoJRMApGwQgEAMMILVQzwap9AAAAAElFTkSuQmCC","orcid":"","institution":"Nanjing Normal University","correspondingAuthor":true,"prefix":"","firstName":"Bin","middleName":"","lastName":"Li","suffix":""},{"id":606301205,"identity":"38f3c0f8-470d-43e8-b22b-e86e98496605","order_by":2,"name":"Zhixing Xu","email":"","orcid":"","institution":"Nanjing Normal University","correspondingAuthor":false,"prefix":"","firstName":"Zhixing","middleName":"","lastName":"Xu","suffix":""},{"id":606301206,"identity":"2b192df6-3b81-4c95-8e69-ef2dda598fa3","order_by":3,"name":"Shiyan Ou","email":"","orcid":"","institution":"Nanjing University","correspondingAuthor":false,"prefix":"","firstName":"Shiyan","middleName":"","lastName":"Ou","suffix":""}],"badges":[],"createdAt":"2025-11-22 08:53:37","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8179135/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8179135/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104782227,"identity":"9cd94274-e782-46e9-bf2e-9d851a1b7076","added_by":"auto","created_at":"2026-03-17 07:57:00","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":528790,"visible":true,"origin":"","legend":"","description":"","filename":"SemPhoPaperSubmission2sub.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8179135/v1_covered_2a59f01d-88d4-40ca-ac99-c4539ae31769.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Character Semantic-Phonetic Structure Enhance Language Models in Classical Chinese","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":"humanities-and-social-sciences-communications","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"palcomms","sideBox":"Learn more about [Humanities \u0026 Social Sciences Communications](http://www.nature.com/palcomms/)","snPcode":"41599","submissionUrl":"https://submission.springernature.com/new-submission/41599/3","title":"Humanities and Social Sciences Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Nature AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-8179135/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8179135/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Writing systems, as fundamental media for human knowledge preservation and facilitating sociocultural interaction, embody the cognitive characteristics of diverse cultures. Despite the rapid advancement of artificial intelligence and language modeling, mainstream language models remain focused on word-level representations, neglecting the rich semantic and structural information embedded within individual characters. In this work, we present an attempt to integrate semantic-phonetic structural information into language modeling, leveraging classical Chinese as the underlying representative system. Our semantic-phonetic-aware language model achieves significant performance gains over the baseline on two core Classical Chinese processing tasks: Word Segmentation and Part-of-Speech Tagging, unveiling the critical role of internal character structure in enhancing language models' representation and encoding capabilities. Through extensive evaluation and in-depth analysis, we reveal that the improvement originates from the synergistic interaction between semantic and phonetic components, as well as the sequential organization of the semantic-phonetic structure. We further argue that achieving the optimal balance between these components is crucial for enhancing the expressiveness and generalizability of language representations. Overall, our findings highlight that the internal organization of characters not only reflects deeper structural principles of the writing system but also opens up a new paradigm for advancing language model design. ","manuscriptTitle":"Character Semantic-Phonetic Structure Enhance Language Models in Classical Chinese","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-16 01:34:35","doi":"10.21203/rs.3.rs-8179135/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-04-10T04:33:44+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"210304315368434888246268146753097058220","date":"2026-04-05T15:45:35+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"215748202338534527999073605102040646223","date":"2026-03-18T13:43:45+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"155752089445625432103986236153892332512","date":"2026-03-12T21:09:18+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-12T16:21:48+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-03-11T14:21:29+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-12-03T11:05:31+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-11-27T06:38:11+00:00","index":"","fulltext":""},{"type":"submitted","content":"Humanities and Social Sciences Communications","date":"2025-11-22T08:49:54+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"humanities-and-social-sciences-communications","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"palcomms","sideBox":"Learn more about [Humanities \u0026 Social Sciences Communications](http://www.nature.com/palcomms/)","snPcode":"41599","submissionUrl":"https://submission.springernature.com/new-submission/41599/3","title":"Humanities and Social Sciences Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Nature AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"53d8859a-b229-42f2-807f-da7d9f925a8d","owner":[],"postedDate":"March 16th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":64521532,"name":"Humanities/Language and linguistics"},{"id":64521533,"name":"Social science/Language and linguistics"},{"id":64521534,"name":"Humanities/Literature"}],"tags":[],"updatedAt":"2026-03-16T01:34:35+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-16 01:34:35","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8179135","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8179135","identity":"rs-8179135","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}