Evolutionary Feature-wise Thresholding for Binary Representation of NLP Embeddings

Evolutionary Feature-wise Thresholding for Binary Representation of NLP Embeddings | 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 Evolutionary Feature-wise Thresholding for Binary Representation of NLP Embeddings Soumen Sinha, Shahryar Rahnamayan, Azam Asilian Bidgoli This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7724663/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract Efficient text embedding is crucial for large-scale natural language processing (NLP) applications, where storage and computational efficiency are key concerns. In this paper, we explore how using binary representations (barcodes) instead of real-valued features can be used for NLP embeddings derived from machine learning models such as BERT. Thresholding is a common method for converting continuous embeddings into binary representations, often using a fixed threshold across all features. We propose a Coordinate Search-based optimization framework that instead identifies the optimal threshold for each feature, demonstrating that feature-specific thresholds lead to improved performance in binary encoding. This ensures that the binary representations are both accurate and efficient, enhancing performance across various features. Our optimal barcode representations have shown promising results in various NLP applications, demonstrating their potential to transform text representation. We conducted extensive experiments and statistical tests on different NLP tasks and datasets to evaluate our approach and compare it to other thresholding methods. Binary embeddings generated using using optimal thresholds found by our method outperform traditional binarization methods in accuracy. This technique for generating binary representations is versatile and can be applied to any features, not just limited to NLP embeddings, making it useful for a wide range of domains in machine learning applications. NLP Coordinate Search Optimal Threshold Barcode representation Optimization Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 21 Apr, 2026 Reviews received at journal 14 Jan, 2026 Reviewers agreed at journal 30 Dec, 2025 Reviewers invited by journal 05 Dec, 2025 Editor assigned by journal 20 Oct, 2025 Submission checks completed at journal 27 Sep, 2025 First submitted to journal 26 Sep, 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-7724663","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":555832458,"identity":"183c7195-4ee2-48d3-bf29-486c248235f9","order_by":0,"name":"Soumen Sinha","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABFUlEQVRIie2RsWrDMBBAzxjsRapXmQz9BZkObSEkvxIT6GQKpRAKDYlLwFr0AQ31h7SbQBAvIXO62WTI4qHQve0JvNUqGTvoDXdwp8edJACH45+ivBwgCjFA0JUIXEWYPPWXEkuTAnPaN4HF0rRsY4zCnycnKud52Oi71xHw+Hg8kNnwdgzRhrUPjI2Bqj6FK8L1ejuFy0GWrMju5h6nBHG5ZYzA2aRXwR00Lfzl20vmrWihU4nKgBZsQYBwy2I1Kkvg71WDynenfJkp/QpekKOige8hQUV1Sm5XuCZGqfCRs2Rd7qap1P7FdblBRVsWE+LwSYtH/Mqq/mhno1SIp2bfzocsFDKp+xbz7ZXfLYfD4XCcyA8i6Vt48C4hsAAAAABJRU5ErkJggg==","orcid":"","institution":"Delft University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Soumen","middleName":"","lastName":"Sinha","suffix":""},{"id":555832459,"identity":"7342669b-38c1-42d6-baf8-fbbe9fcac9f5","order_by":1,"name":"Shahryar Rahnamayan","email":"","orcid":"","institution":"Brock University","correspondingAuthor":false,"prefix":"","firstName":"Shahryar","middleName":"","lastName":"Rahnamayan","suffix":""},{"id":555832460,"identity":"cd174b15-f3ec-49d9-ba54-68e309a4155d","order_by":2,"name":"Azam Asilian Bidgoli","email":"","orcid":"","institution":"Wilfrid Laurier University","correspondingAuthor":false,"prefix":"","firstName":"Azam","middleName":"Asilian","lastName":"Bidgoli","suffix":""}],"badges":[],"createdAt":"2025-09-26 20:38:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7724663/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7724663/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":97684680,"identity":"51df4cbe-eb2f-4de0-8d9d-b2265bfa028c","added_by":"auto","created_at":"2025-12-08 10:07:55","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2447783,"visible":true,"origin":"","legend":"","description":"","filename":"FinalSpringer.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7724663/v1/1b4cd18a4ca7f8620a7de64b.pdf"},{"id":97684656,"identity":"227da31d-e90f-459b-9568-ff53a98c1da2","added_by":"auto","created_at":"2025-12-08 10:07:37","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4992,"visible":true,"origin":"","legend":"","description":"","filename":"2f7eabdc85ef4dc6b52ec00d662025ef.json","url":"https://assets-eu.researchsquare.com/files/rs-7724663/v1/76a403be11fede26484183e3.json"},{"id":97684688,"identity":"8bc11130-8bce-4373-a2a5-d2a63ffeadda","added_by":"auto","created_at":"2025-12-08 10:08:01","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1620389,"visible":true,"origin":"","legend":"","description":"","filename":"FinalSpringer.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7724663/v1_covered_92d890f3-bf7e-4ca3-ba26-ec250d796e48.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Evolutionary Feature-wise Thresholding for Binary Representation of NLP Embeddings","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":"international-journal-of-data-science-and-analytics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jdsa","sideBox":"Learn more about [International Journal of Data Science and Analytics](http://link.springer.com/journal/41060)","snPcode":"41060","submissionUrl":"https://submission.nature.com/new-submission/41060/3","title":"International Journal of Data Science and Analytics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"NLP, Coordinate Search, Optimal Threshold, Barcode representation, Optimization","lastPublishedDoi":"10.21203/rs.3.rs-7724663/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7724663/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Efficient text embedding is crucial for large-scale natural language processing (NLP) applications, where storage and computational efficiency are key concerns. In this paper, we explore how using binary representations (barcodes) instead of real-valued features can be used for NLP embeddings derived from machine learning models such as BERT. Thresholding is a common method for converting continuous embeddings into binary representations, often using a fixed threshold across all features. We propose a Coordinate Search-based optimization framework that instead identifies the optimal threshold for each feature, demonstrating that feature-specific thresholds lead to improved performance in binary encoding. This ensures that the binary representations are both accurate and efficient, enhancing performance across various features. Our optimal barcode representations have shown promising results in various NLP applications, demonstrating their potential to transform text representation. We conducted extensive experiments and statistical tests on different NLP tasks and datasets to evaluate our approach and compare it to other thresholding methods. Binary embeddings generated using using optimal thresholds found by our method outperform traditional binarization methods in accuracy. This technique for generating binary representations is versatile and can be applied to any features, not just limited to NLP embeddings, making it useful for a wide range of domains in machine learning applications.","manuscriptTitle":"Evolutionary Feature-wise Thresholding for Binary Representation of NLP Embeddings","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-08 10:04:53","doi":"10.21203/rs.3.rs-7724663/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"239846498924765293565889547987659440381","date":"2026-04-21T17:33:44+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-14T19:14:54+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"284943631394734203327754527084187231367","date":"2025-12-30T06:36:54+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-12-05T13:17:12+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-10-20T08:58:17+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-27T10:23:15+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal of Data Science and Analytics","date":"2025-09-26T20:22:11+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"international-journal-of-data-science-and-analytics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jdsa","sideBox":"Learn more about [International Journal of Data Science and Analytics](http://link.springer.com/journal/41060)","snPcode":"41060","submissionUrl":"https://submission.nature.com/new-submission/41060/3","title":"International Journal of Data Science and Analytics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"7d2ad43f-1028-4f45-bf19-2124d88af13e","owner":[],"postedDate":"December 8th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-12-08T10:04:53+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-08 10:04:53","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7724663","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7724663","identity":"rs-7724663","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}