EEE-MT: Enhanced Entity Encoding for Low-Resource Machine Translation

EEE-MT: Enhanced Entity Encoding for Low-Resource Machine Translation | 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 EEE-MT: Enhanced Entity Encoding for Low-Resource Machine Translation Xiaocong Wang, Ying Li, Shengxiang Gao, Yuxin Huang, Zhengtao Yu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7969437/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 Low-resource language translation faces significant challenges in entity coverage and contextual information utilization, leading to high entity translation error rates. To address these issues, this paper proposes an entity-enhanced encoding mechanism by integrating an entity-enhanced encoder into the Transformer architecture to strengthen the model's ability to represent entities with fine-grained differentiation. The mechanism leverages the synergistic interaction between the self-attention mechanism and the enhanced encoder, coupled with a masking strategy, to comprehensively leverages contextual information for entities. Furthermore, a multi-task joint optimization framework is introduced, incorporating entity prediction losses at both the encoder and decoder to enhance the model's sensitivity to entity-related features. We demonstrate the effectiveness of EEE-MT with the experiments on machine translation tasks of IWSLT14 English-German, IWSLT15 English-Vietnamese, IWSLT17 English-French and English-Chinese, EEE-MT method achieves an improvement of 2.37–3.84 BLEU score on the four tasks. In low-resource translation tasks such as Lao-Chinese and Myanmar-Chinese, the translation performance of EEE-MT surpasses that of mainstream large language models. Neural Machine Translation Enhanced Encoding Entity Translation 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-7969437","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":538890477,"identity":"dc12a889-a0b7-44e4-8231-def8ffd49c57","order_by":0,"name":"Xiaocong Wang","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Xiaocong","middleName":"","lastName":"Wang","suffix":""},{"id":538890478,"identity":"163070dc-5d39-4623-8127-ad07ef195646","order_by":1,"name":"Ying Li","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Ying","middleName":"","lastName":"Li","suffix":""},{"id":538890479,"identity":"810ae469-ee53-446d-8e68-0aec69176522","order_by":2,"name":"Shengxiang Gao","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Shengxiang","middleName":"","lastName":"Gao","suffix":""},{"id":538890480,"identity":"0484594e-8bea-4e2e-9c81-4652bd5db3ee","order_by":3,"name":"Yuxin Huang","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Yuxin","middleName":"","lastName":"Huang","suffix":""},{"id":538890481,"identity":"2599679d-9a34-4fd7-81fd-63016681fac8","order_by":4,"name":"Zhengtao Yu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAt0lEQVRIiWNgGAWjYLCCjw0gkrHxAHHK2YBqZzYwSACpBuK1MPOCtTAwEKdFfn6PmbTtDps63fbDQFtqbKIJamFs4zGTzj2TJmF2JhGo5VhabgMhLcxsIC1thyXMDgC1MDYcJqyFDaTFEqTl/EMitfCAtDCCtNwg1hYJtrRiy962NMltN4C2JBDjF/nmwxtv/Gyz4Tc7n/7wwYcaG8JaGBg4DBDsBMLKQYD9AXHqRsEoGAWjYOQCALHAPvCMv1apAAAAAElFTkSuQmCC","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Zhengtao","middleName":"","lastName":"Yu","suffix":""}],"badges":[],"createdAt":"2025-10-28 16:44:27","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7969437/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7969437/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":95708957,"identity":"57434744-ab62-428c-adbd-7178f9898093","added_by":"auto","created_at":"2025-11-12 07:32:33","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6155,"visible":true,"origin":"","legend":"","description":"","filename":"d8fd04440da64ce297954a9723148e6e.json","url":"https://assets-eu.researchsquare.com/files/rs-7969437/v1/ac02da40ebeac4f5d76b1eb0.json"},{"id":102295764,"identity":"88f42eb8-5497-47c3-b53b-b019d2093ca3","added_by":"auto","created_at":"2026-02-10 10:14:51","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":6509713,"visible":true,"origin":"","legend":"","description":"","filename":"EEEMTEnhancedEntityEncodingforLowResourceMachineTranslation.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7969437/v1_covered_16072596-cef8-4bf5-9af1-c044916583c3.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"EEE-MT: Enhanced Entity Encoding for Low-Resource Machine Translation","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":"Neural Machine Translation, Enhanced Encoding, Entity Translation","lastPublishedDoi":"10.21203/rs.3.rs-7969437/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7969437/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Low-resource language translation faces significant challenges in entity coverage and contextual information utilization, leading to high entity translation error rates. To address these issues, this paper proposes an entity-enhanced encoding mechanism by integrating an entity-enhanced encoder into the Transformer architecture to strengthen the model's ability to represent entities with fine-grained differentiation. The mechanism leverages the synergistic interaction between the self-attention mechanism and the enhanced encoder, coupled with a masking strategy, to comprehensively leverages contextual information for entities. Furthermore, a multi-task joint optimization framework is introduced, incorporating entity prediction losses at both the encoder and decoder to enhance the model's sensitivity to entity-related features. We demonstrate the effectiveness of EEE-MT with the experiments on machine translation tasks of IWSLT14 English-German, IWSLT15 English-Vietnamese, IWSLT17 English-French and English-Chinese, EEE-MT method achieves an improvement of 2.37–3.84 BLEU score on the four tasks. In low-resource translation tasks such as Lao-Chinese and Myanmar-Chinese, the translation performance of EEE-MT surpasses that of mainstream large language models.","manuscriptTitle":"EEE-MT: Enhanced Entity Encoding for Low-Resource Machine Translation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-12 07:32:28","doi":"10.21203/rs.3.rs-7969437/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":"10f745fd-b75d-4750-865e-1c658e2de6a8","owner":[],"postedDate":"November 12th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-02-06T05:55:14+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-12 07:32:28","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7969437","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7969437","identity":"rs-7969437","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}