Tenyidie Named Entity Recognition - Corpus creation and Machine/Deep Learning applications

Tenyidie Named Entity Recognition - Corpus creation and Machine/Deep Learning applications | 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 Tenyidie Named Entity Recognition - Corpus creation and Machine/Deep Learning applications Teisovi Angami, Themrichon Tuithung This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3621158/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 26 Dec, 2025 Read the published version in Language Resources and Evaluation → Version 1 posted 4 You are reading this latest preprint version Abstract The Tenyidie language, a.k.a, the Angami language is a low-resource languagebelonging to the Tibeto-Burman language family and is considered a major language of Nagaland in the north-eastern part of India. Among the many NaturalLanguage Processing (NLP) tasks, named entity recognition (NER) is an important task in which named entities such as person, organization, location, etc, areidentified and find its applications in many other applications such as classifying content for news providers, recommendation systems, sentiment analysis, etc.To the best of the authors’ knowledge, this is the first attempt at building NERfor the Tenyidie language. The main aim of this research is to develop and evaluate the Named Entity Recognition (NER) annotated corpus for the TenyidieLanguage. In this work, a NER annotated dataset of 10,000 sentences (211,364tokens) for Tenyidie Language comprising of 5,208 named entities (699 persons,2,089 organizations, and 2,420 location entities) has been created. This paperalso applies the Machine Learning/Deep Learning techniques to the created NERdataset for the Tenyidie Language. For deep learning, we have explored different word embedding methods like word2vec, GloVe, fasttext, and BERT. In ourexperiments conducted, we achieved the best f1-score using the BERT-BASE(cased) model. The main contributions of this research are the creation of an NER annotated dataset for the Tenyidie language and the evaluation of the NERdataset using different learning techniques such as CRF, BLSTM, including thestate-of-the-art BERT model. Tenyidie Nagaland Tibeto-Burman NLP NER CRF BLSTM BERT Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 26 Dec, 2025 Read the published version in Language Resources and Evaluation → Version 1 posted Editorial decision: Accepted 24 Nov, 2025 Editor assigned by journal 24 Nov, 2025 Submission checks completed at journal 01 Sep, 2025 First submitted to journal 31 Aug, 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-3621158","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":508651833,"identity":"778b30a1-fbdd-4127-a8cc-8badb9c28981","order_by":0,"name":"Teisovi Angami","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwklEQVRIiWNgGAWjYFACxgYgISEHYh54QIwGHqgWY7CWBOK0QEAiSCMDUVrs2ZubP3xss0ifH3b4IdAWOzndBkK28Bxsk5zZJpG78XaaAVBLsrHZAUJaJBLbmHnOALXMTgBpOZC4jaAW+YfNn4Fa0g1np38gUosEY4M0T4VEgrx0DrG2nElsk5xRIWG4QTqn4ECCARF+YW8//vjDB4M6efnZ6Zs/fKiwkyOoBQ4MwCoNiFUOAvINpKgeBaNgFIyCEQUAEu9Ca6uVClcAAAAASUVORK5CYII=","orcid":"","institution":"National Institute of Technology Nagaland","correspondingAuthor":true,"prefix":"","firstName":"Teisovi","middleName":"","lastName":"Angami","suffix":""},{"id":508651834,"identity":"ef61072e-940b-48e1-ac14-fe7df24963a2","order_by":1,"name":"Themrichon Tuithung","email":"","orcid":"","institution":"National Institute of Technology Nagaland","correspondingAuthor":false,"prefix":"","firstName":"Themrichon","middleName":"","lastName":"Tuithung","suffix":""}],"badges":[],"createdAt":"2023-11-16 15:29:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3621158/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3621158/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s10579-025-09880-x","type":"published","date":"2025-12-26T15:58:06+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":95347983,"identity":"15bbd4e1-d7dc-462c-b85c-7e29bdd93a43","added_by":"auto","created_at":"2025-11-07 03:52:57","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5228,"visible":true,"origin":"","legend":"","description":"","filename":"78b9f32aa75e445ca65524c3a0c9e31f.json","url":"https://assets-eu.researchsquare.com/files/rs-3621158/v1/b83e871dd18e6f2394c670f5.json"},{"id":99172489,"identity":"0e74525e-2bc4-4acb-ae6d-8b493426c281","added_by":"auto","created_at":"2025-12-29 16:10:25","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":594300,"visible":true,"origin":"","legend":"","description":"","filename":"TenyidieNamedEntityRecognitionSpringerSEPT2025REVISION.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3621158/v1_covered_27b12105-684a-45ab-9f44-e07cbf934d99.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Tenyidie Named Entity Recognition - Corpus creation and Machine/Deep Learning applications","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"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":"Tenyidie, Nagaland, Tibeto-Burman, NLP, NER, CRF, BLSTM, BERT","lastPublishedDoi":"10.21203/rs.3.rs-3621158/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3621158/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The Tenyidie language, a.k.a, the Angami language is a low-resource languagebelonging to the Tibeto-Burman language family and is considered a major language of Nagaland in the north-eastern part of India. Among the many NaturalLanguage Processing (NLP) tasks, named entity recognition (NER) is an important task in which named entities such as person, organization, location, etc, areidentified and find its applications in many other applications such as classifying content for news providers, recommendation systems, sentiment analysis, etc.To the best of the authors’ knowledge, this is the first attempt at building NERfor the Tenyidie language. The main aim of this research is to develop and evaluate the Named Entity Recognition (NER) annotated corpus for the TenyidieLanguage. In this work, a NER annotated dataset of 10,000 sentences (211,364tokens) for Tenyidie Language comprising of 5,208 named entities (699 persons,2,089 organizations, and 2,420 location entities) has been created. This paperalso applies the Machine Learning/Deep Learning techniques to the created NERdataset for the Tenyidie Language. For deep learning, we have explored different word embedding methods like word2vec, GloVe, fasttext, and BERT. In ourexperiments conducted, we achieved the best f1-score using the BERT-BASE(cased) model. The main contributions of this research are the creation of an NER annotated dataset for the Tenyidie language and the evaluation of the NERdataset using different learning techniques such as CRF, BLSTM, including thestate-of-the-art BERT model. ","manuscriptTitle":"Tenyidie Named Entity Recognition - Corpus creation and Machine/Deep Learning applications","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-07 03:52:53","doi":"10.21203/rs.3.rs-3621158/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Accepted","date":"2025-11-24T11:58:09+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-11-24T11:56:24+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-01T16:00:54+00:00","index":"","fulltext":""},{"type":"submitted","content":"Language Resources and Evaluation","date":"2025-08-31T17:08:06+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":"f053409c-bd4a-45b3-afc3-789b76046a33","owner":[],"postedDate":"November 7th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-12-29T16:05:55+00:00","versionOfRecord":{"articleIdentity":"rs-3621158","link":"https://doi.org/10.1007/s10579-025-09880-x","journal":{"identity":"language-resources-and-evaluation","isVorOnly":false,"title":"Language Resources and Evaluation"},"publishedOn":"2025-12-26 15:58:06","publishedOnDateReadable":"December 26th, 2025"},"versionCreatedAt":"2025-11-07 03:52:53","video":"","vorDoi":"10.1007/s10579-025-09880-x","vorDoiUrl":"https://doi.org/10.1007/s10579-025-09880-x","workflowStages":[]},"version":"v1","identity":"rs-3621158","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3621158","identity":"rs-3621158","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}