Towards Multilingual Machine Translation for Low-Resource South Asian Languages: A Transformer-Based Approach on English–Urdu–Kashmiri

Towards Multilingual Machine Translation for Low-Resource South Asian Languages: A Transformer-Based Approach on English–Urdu–Kashmiri | 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 Towards Multilingual Machine Translation for Low-Resource South Asian Languages: A Transformer-Based Approach on English–Urdu–Kashmiri Shah Raashed Ul Shams, Kaisar Javeed Giri This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7398007/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 Machine translation remains a significant challenge for natural language processing in low-resource languages, particularly within linguistically diverse regions such as South Asia. To address the scarcity of translation resources for Kashmiri and Urdu, a high-quality multilingual parallel corpus was constructed. This corpus comprises over 26,000 English sentences that have been manually translated and aligned with their Urdu and Kashmiri equivalents. The dataset was further expanded by incorporating translations into Urdu and integrating a publicly available English–Kashmiri corpus containing 16,000 samples. The NLLB-200 multilingual model was fine-tuned for English–Kashmiri and English–Urdu translation using this dataset. The model achieved BLEU scores of 35.6 and 36.13 for English–Urdu across multiple runs. For English–Kashmiri, BLEU scores improved from 6.28 and 5.68 to 17.9 and 18.29 after fine-tuning. These results demonstrate a substantial improvement in translation performance compared to zero-shot baselines. Qualitative evaluation further indicates enhanced fluency and grammatical accuracy in the model outputs. Statistical analysis and visualizations provide additional support for these findings. The resulting resources and methodologies can inform the development of future multilingual and bidirectional machine translation systems for underrepresented languages, including Kashmiri, Urdu, and English. Low-Resource Machine Translation Kashmiri Language Processing NLLB-200 Model Back-Translation Augmentation Fine-Tuning Transformers BLEU Score Evaluation 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-7398007","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":503892439,"identity":"c7da0657-4777-484f-8e1c-c3bb8f994e82","order_by":0,"name":"Shah Raashed Ul Shams","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA80lEQVRIiWNgGAWjYDACCQY2GINB4oMBTNgAl3o0LZIzgCp5SNIiDVLOQ8hd8rObnz1g3GMnD2QcvG1TcNjenoH54QeGgjs4tRjcOWZuwPAs2XDDnWPJ1jkGhxN7GNiMJRgMnuHWIpFgJsFwgJlxg0SOmTRQSwLQYWZA8cO4HTYj/RtQS739/Bn536QtDA7b8zCwf8OrheFGDsiWw4kNN3LYpIEqGXsYePDbYnAjp0wi4cDx5A030owtewzSE3sO8xRLJOB32DaJDweqbefPSH5448cfa3v29vaNHz78weMwEEhA4TFjiIyCUTAKRsEoIBUAALxETV5lLOnRAAAAAElFTkSuQmCC","orcid":"","institution":"Islamic University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Shah","middleName":"Raashed Ul","lastName":"Shams","suffix":""},{"id":503892440,"identity":"70ca9c96-cdcc-48de-8710-bbe835512774","order_by":1,"name":"Kaisar Javeed Giri","email":"","orcid":"","institution":"Islamic University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Kaisar","middleName":"Javeed","lastName":"Giri","suffix":""}],"badges":[],"createdAt":"2025-08-18 09:23:37","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7398007/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7398007/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":89907538,"identity":"5da2f38c-97e5-4d10-8f83-c90d7965617f","added_by":"auto","created_at":"2025-08-26 10:19:02","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":431814,"visible":true,"origin":"","legend":"","description":"","filename":"EnglishUrduKashmiriTransModel.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7398007/v1_covered_b7da307d-a246-4265-a0b1-4637c51fc7c7.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Towards Multilingual Machine Translation for Low-Resource South Asian Languages: A Transformer-Based Approach on English–Urdu–Kashmiri","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"Low-Resource Machine Translation, Kashmiri Language Processing, NLLB-200 Model, Back-Translation Augmentation, Fine-Tuning Transformers, BLEU Score Evaluation","lastPublishedDoi":"10.21203/rs.3.rs-7398007/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7398007/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\nMachine translation remains a significant challenge for natural language processing in low-resource languages, particularly within linguistically diverse regions such as South Asia. To address the scarcity of translation resources for Kashmiri and Urdu, a high-quality multilingual parallel corpus was constructed. This corpus comprises over 26,000 English sentences that have been manually translated and aligned with their Urdu and Kashmiri equivalents. The dataset was further expanded by incorporating translations into Urdu and integrating a publicly available English–Kashmiri corpus containing 16,000 samples. The NLLB-200 multilingual model was fine-tuned for English–Kashmiri and English–Urdu translation using this dataset. The model achieved BLEU scores of 35.6 and 36.13 for English–Urdu across multiple runs. For English–Kashmiri, BLEU scores improved from 6.28 and 5.68 to 17.9 and 18.29 after fine-tuning. These results demonstrate a substantial improvement in translation performance compared to zero-shot baselines. Qualitative evaluation further indicates enhanced fluency and grammatical accuracy in the model outputs. Statistical analysis and visualizations provide additional support for these findings. The resulting resources and methodologies can inform the development of future multilingual and bidirectional machine translation systems for underrepresented languages, including Kashmiri, Urdu, and English.","manuscriptTitle":"Towards Multilingual Machine Translation for Low-Resource South Asian Languages: A Transformer-Based Approach on English–Urdu–Kashmiri","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-26 10:10:57","doi":"10.21203/rs.3.rs-7398007/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":"e886baa7-cee0-4109-a136-e97edd22f372","owner":[],"postedDate":"August 26th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-08-26T10:10:57+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-26 10:10:57","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7398007","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7398007","identity":"rs-7398007","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}