Dual-BERT Adversarial Model for Text Normalization in Hausa User-Generated Contents

Dual-BERT Adversarial Model for Text Normalization in Hausa User-Generated Contents | 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 Method Article Dual-BERT Adversarial Model for Text Normalization in Hausa User-Generated Contents Abubakar Ahmad Aliero, Sulaimon Adebayo Bashir, Hamzat Olanrewaju Aliyu, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7446019/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 This paper presents an innovative Dual-BERT Generative Adversarial Networks framework aimed at improving text normalisation in low-resource languages, specifically Hausa. By harnessing the capabilities of Bidirectional Encoder Representations from Transformers (BERT) and Generative Adversarial Networks (GANs), the model surpasses conventional Transformer-based and standalone GAN models in Exact Match, Word Error Rate (WER), Character Error Rate (CER), and BLEU score. Experimental results indicate an Exact Match of 0.80 and a notable decrease in error rates across all metrics. This methodology enhances NLP tools for under-represented languages, particularly within noisy, informal textual contexts such as social media. Text normalization User-Generated Content Under-resourced Languages BERT GAN Neural 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-7446019","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Method Article","associatedPublications":[],"authors":[{"id":532320308,"identity":"980a27d6-cecb-4a49-a7a0-708d0e59c9e1","order_by":0,"name":"Abubakar Ahmad Aliero","email":"data:image/png;base64,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","orcid":"","institution":"Federal University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Abubakar","middleName":"Ahmad","lastName":"Aliero","suffix":""},{"id":532320309,"identity":"5ebdee3c-6474-4403-9b1e-e6a4e6c4a4ff","order_by":1,"name":"Sulaimon Adebayo Bashir","email":"","orcid":"","institution":"Federal University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Sulaimon","middleName":"Adebayo","lastName":"Bashir","suffix":""},{"id":532320310,"identity":"3d8d5b5a-f522-49e4-bf8e-944bda29ffc9","order_by":2,"name":"Hamzat Olanrewaju Aliyu","email":"","orcid":"","institution":"Federal University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Hamzat","middleName":"Olanrewaju","lastName":"Aliyu","suffix":""},{"id":532320311,"identity":"e0b4944c-d1fe-4edd-8ba5-6094b2eff4b9","order_by":3,"name":"Amina Gogo Tafida","email":"","orcid":"","institution":"Federal University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Amina","middleName":"Gogo","lastName":"Tafida","suffix":""},{"id":532320312,"identity":"f7a12e30-404c-49ab-b70f-19aa7616d8a5","order_by":4,"name":"Mukhtar Ibrahim Hussaini","email":"","orcid":"","institution":"Rayhaan University Birnin Kebbi","correspondingAuthor":false,"prefix":"","firstName":"Mukhtar","middleName":"Ibrahim","lastName":"Hussaini","suffix":""}],"badges":[],"createdAt":"2025-08-24 12:08:13","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7446019/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7446019/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":94362067,"identity":"07303187-2b62-4cdd-85c1-7bd405a46383","added_by":"auto","created_at":"2025-10-27 13:04:44","extension":"doc","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":624128,"visible":true,"origin":"","legend":"","description":"","filename":"DiscoverCompuitngAbubakarAliero.doc","url":"https://assets-eu.researchsquare.com/files/rs-7446019/v1/1655a197adc4c394999e808e.doc"},{"id":94362219,"identity":"2920cea0-d728-486f-a663-3e659f39f67e","added_by":"auto","created_at":"2025-10-27 13:04:52","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6875,"visible":true,"origin":"","legend":"","description":"","filename":"68b9b35d1f854800a6b5a7ec0788c2b8.json","url":"https://assets-eu.researchsquare.com/files/rs-7446019/v1/0156c0fd03104646b62a55f7.json"},{"id":94361936,"identity":"6c175cc4-6daa-452c-ab1e-73655678358b","added_by":"auto","created_at":"2025-10-27 13:04:39","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":77776,"visible":true,"origin":"","legend":"","description":"","filename":"68b9b35d1f854800a6b5a7ec0788c2b81enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7446019/v1/21504a1794a9c8132ec7e97b.xml"},{"id":94362925,"identity":"e6af2780-086a-4a7f-ba9f-3a989b879d3d","added_by":"auto","created_at":"2025-10-27 13:05:43","extension":"xml","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":76944,"visible":true,"origin":"","legend":"","description":"","filename":"68b9b35d1f854800a6b5a7ec0788c2b81structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7446019/v1/6d89383f064637bc67838fa1.xml"},{"id":94362279,"identity":"3d37d40e-da7b-4633-af7a-89d21ccefe94","added_by":"auto","created_at":"2025-10-27 13:04:55","extension":"html","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":88966,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7446019/v1/dc369ba4c8988ec14fe44eac.html"},{"id":97961799,"identity":"0d1f5edb-9771-4bd1-a838-80fe11e605d2","added_by":"auto","created_at":"2025-12-11 08:54:47","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":501383,"visible":true,"origin":"","legend":"","description":"","filename":"DiscoverCompuitngAbubakarAliero.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7446019/v1_covered_d520e7ca-07f2-4d9e-aa19-e101d2b5ba71.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Dual-BERT Adversarial Model for Text Normalization in Hausa User-Generated Contents","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":"Text normalization, User-Generated Content, Under-resourced Languages, BERT, GAN, Neural Network","lastPublishedDoi":"10.21203/rs.3.rs-7446019/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7446019/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis paper presents an innovative Dual-BERT Generative Adversarial Networks framework aimed at improving text normalisation in low-resource languages, specifically Hausa. By harnessing the capabilities of Bidirectional Encoder Representations from Transformers (BERT) and Generative Adversarial Networks (GANs), the model surpasses conventional Transformer-based and standalone GAN models in Exact Match, Word Error Rate (WER), Character Error Rate (CER), and BLEU score. Experimental results indicate an Exact Match of 0.80 and a notable decrease in error rates across all metrics. This methodology enhances NLP tools for under-represented languages, particularly within noisy, informal textual contexts such as social media.\u003c/p\u003e","manuscriptTitle":"Dual-BERT Adversarial Model for Text Normalization in Hausa User-Generated Contents","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-24 18:11:31","doi":"10.21203/rs.3.rs-7446019/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":"73308c63-f094-4905-b300-a833ed1cc889","owner":[],"postedDate":"October 24th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-12-11T08:54:34+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-24 18:11:31","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7446019","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7446019","identity":"rs-7446019","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}