GinLish Corpus v0.1.0 - Development and Evaluation of Low-Resource Tagin-English Parallel Corpus

GinLish Corpus v0.1.0 - Development and Evaluation of Low-Resource Tagin-English Parallel Corpus | 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 GinLish Corpus v0.1.0 - Development and Evaluation of Low-Resource Tagin-English Parallel Corpus Tungon Dugi, Koj Sambyo This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6814591/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 4 You are reading this latest preprint version Abstract This paper introduces GinLish Corpus v0.1.0, the inaugural Tagin-English parallel corpus, addressing a critical gap in resources for the definitely endangered Tagin language, a Tani language of the Sino-Tibetan family spoken in Arunachal Pradesh, India. Prior to this work, there were likely very few or no online resources available for Tagin language, making this corpus uniquely valuable. Our dataset comprises 35,000 meticulously collected and aligned English and Tagin sentence pairs. We leverage this corpus to conduct a comprehensive Neural Machine Translation (NMT) study, comparing the performance of various architectures including Recurrent Neural Networks (RNN), and Transformers, evaluated using BLEU, METEOR, chrF, and TER scores. Our results demonstrate that the RNN model achieved the best performance among the architectures, with BLEU scores of 26.07 and 25.12 for English-to-Tagin and Tagin-to-English translations, respectively. In contrast, the Transformer model underperformed, with BLEU scores of 22.14 for English-to-Tagin and 20.28 for Tagin-to-English translations. Our findings lay the groundwork for future research in Tagin language technology, aiding in language preservation and expanding NMT reach to extremely low-resource languages. Machine Translation Low-Resource Parallel Corpus Language Documentation Neural Machine Translation Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers invited by journal 23 Jun, 2025 Editor assigned by journal 09 Jun, 2025 Submission checks completed at journal 04 Jun, 2025 First submitted to journal 03 Jun, 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-6814591","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":475154883,"identity":"6ba600a9-aa75-4acb-b2a4-89fa23c7fd46","order_by":0,"name":"Tungon Dugi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA10lEQVRIiWNgGAWjYPACZiBiPgBkSMgQVMuD0MKWANLCQ4IWBh4DJAE8wF4i9/CLjzusE+e783x+daPGgoeB/fDRDXhtkchLs5x5Jj1x42HebdY5x4AO40lLu4FfS46ZMW/b4cSNzbzbjHPYgFokeMyI1cLzzDjnH3FajB+DtMxn5mF+nNtGjJYzb8wYZ7alG29gZjNjzu2T4GEj5Bf29hzjDx/brGXn9x9+/DnnW50cP/vhY3i1AAGbBIg0OABlsBFQDgLMH0CkfAOUMQpGwSgYBaMAHQAA0M1DIMGmq/AAAAAASUVORK5CYII=","orcid":"","institution":"National Institute of Technology Arunachal Pradesh","correspondingAuthor":true,"prefix":"","firstName":"Tungon","middleName":"","lastName":"Dugi","suffix":""},{"id":475154884,"identity":"e997f9d7-de62-44a0-99db-b512266dfdb4","order_by":1,"name":"Koj Sambyo","email":"","orcid":"","institution":"National Institute of Technology Arunachal Pradesh","correspondingAuthor":false,"prefix":"","firstName":"Koj","middleName":"","lastName":"Sambyo","suffix":""}],"badges":[],"createdAt":"2025-06-03 21:38:06","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6814591/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6814591/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":85355725,"identity":"3eb93e68-202f-4237-8640-302682cf401d","added_by":"auto","created_at":"2025-06-25 04:48:14","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":928044,"visible":true,"origin":"","legend":"","description":"","filename":"GinLishCorpus.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6814591/v1_covered_5d25ac22-833a-40fa-a777-68d716a2baf1.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"GinLish Corpus v0.1.0 - Development and Evaluation of Low-Resource Tagin-English Parallel Corpus","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":"language-resources-and-evaluation","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"lrev","sideBox":"Learn more about [Language Resources and Evaluation](http://link.springer.com/journal/10579)","snPcode":"10579","submissionUrl":"https://submission.nature.com/new-submission/10579/3","title":"Language Resources and Evaluation","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Machine Translation, Low-Resource Parallel Corpus, Language Documentation, Neural Machine Translation","lastPublishedDoi":"10.21203/rs.3.rs-6814591/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6814591/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis paper introduces GinLish Corpus v0.1.0, the inaugural Tagin-English parallel corpus, addressing a critical gap in resources for the definitely endangered Tagin language, a Tani language of the Sino-Tibetan family spoken in Arunachal Pradesh, India. Prior to this work, there were likely very few or no online resources available for Tagin language, making this corpus uniquely valuable. Our dataset comprises 35,000 meticulously collected and aligned English and Tagin sentence pairs. We leverage this corpus to conduct a comprehensive Neural Machine Translation (NMT) study, comparing the performance of various architectures including Recurrent Neural Networks (RNN), and Transformers, evaluated using BLEU, METEOR, chrF, and TER scores. Our results demonstrate that the RNN model achieved the best performance among the architectures, with BLEU scores of 26.07 and 25.12 for English-to-Tagin and Tagin-to-English translations, respectively. In contrast, the Transformer model underperformed, with BLEU scores of 22.14 for English-to-Tagin and 20.28 for Tagin-to-English translations. Our findings lay the groundwork for future research in Tagin language technology, aiding in language preservation and expanding NMT reach to extremely low-resource languages.\u003c/p\u003e","manuscriptTitle":"GinLish Corpus v0.1.0 - Development and Evaluation of Low-Resource Tagin-English Parallel Corpus","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-25 04:32:08","doi":"10.21203/rs.3.rs-6814591/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewersInvited","content":"","date":"2025-06-23T11:55:47+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-06-09T12:46:09+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-06-04T16:54:19+00:00","index":"","fulltext":""},{"type":"submitted","content":"Language Resources and Evaluation","date":"2025-06-03T21:23:45+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"language-resources-and-evaluation","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"lrev","sideBox":"Learn more about [Language Resources and Evaluation](http://link.springer.com/journal/10579)","snPcode":"10579","submissionUrl":"https://submission.nature.com/new-submission/10579/3","title":"Language Resources and Evaluation","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"70965cbc-45b3-4ac3-9da5-6aec47450048","owner":[],"postedDate":"June 25th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-06-25T04:32:08+00:00","versionOfRecord":[],"versionCreatedAt":"2025-06-25 04:32:08","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6814591","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6814591","identity":"rs-6814591","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}