Computation of Sentence Similarity Score through Hybrid Deep Learning with a Special Focus on Negation Sentence.

Computation of Sentence Similarity Score through Hybrid Deep Learning with a Special Focus on Negation Sentence. | 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 Article Computation of Sentence Similarity Score through Hybrid Deep Learning with a Special Focus on Negation Sentence. Rohit M, Jeganathan L, Srinivasa Rao Ummity, Janaki Meena M, Jayaram Balabaskaran This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6565198/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 28 Feb, 2026 Read the published version in Scientific Reports → Version 1 posted 11 You are reading this latest preprint version Abstract Automated answer script evaluation relies heavily on accurate sentence similarity assessment. Traditional methods often struggle with linguistic nuances, particularly negation, where misinterpretations can lead to incorrect grading and biased assessments. To address these challenges, we propose a hybrid deep learning framework designed to enhance sentence similarity detection, thereby improving the accuracy and reliability of automated evaluation systems. Our model integrates the advanced embedding capabilities of \textbf{BERT, RoBERTa, Sentence-BERT, and Word2Vec} into a unified representation. A Siamese network with a bi-directional LSTM serves as the core computational component, enabling precise similarity scoring. This approach strengthens the model’s ability to understand negated statements and complex sentence structures. We evaluated our model on a specialized dataset containing examples of negations and conjunctions. The results demonstrated a significant improvement over existing methods, achieving an AU-ROC score of 0.984. Additionally, our model outperformed baseline approaches across Mean Absolute Error (MAE), Mean Squared Error (MSE), and R² metrics. These findings confirm the model’s effectiveness and highlight its potential for enhancing automated grading systems and other applications requiring precise interpretation of textual meaning. Physical sciences/Mathematics and computing/Computational science Physical sciences/Mathematics and computing/Computer science Physical sciences/Mathematics and computing/Information technology Physical sciences/Mathematics and computing/Scientific data semantic similarity negation handling conjunction handling Siamese network bi-directional LSTM Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 28 Feb, 2026 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 24 Nov, 2025 Reviews received at journal 21 Nov, 2025 Reviewers agreed at journal 14 Nov, 2025 Reviews received at journal 23 Sep, 2025 Reviewers agreed at journal 16 Sep, 2025 Reviewers agreed at journal 14 Sep, 2025 Reviewers invited by journal 14 Sep, 2025 Editor assigned by journal 06 Aug, 2025 Editor invited by journal 14 May, 2025 Submission checks completed at journal 13 May, 2025 First submitted to journal 30 Apr, 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-6565198","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":515917599,"identity":"e7c1dd5e-8fa1-4ee7-8f3a-1c7abdf02a21","order_by":0,"name":"Rohit M","email":"","orcid":"","institution":"Vellore Institute of Technology University","correspondingAuthor":false,"prefix":"","firstName":"Rohit","middleName":"","lastName":"M","suffix":""},{"id":515917600,"identity":"92a41340-b95f-4e23-b6da-2f3b44d48e04","order_by":1,"name":"Jeganathan L","email":"","orcid":"","institution":"Vellore Institute of Technology University","correspondingAuthor":false,"prefix":"","firstName":"Jeganathan","middleName":"","lastName":"L","suffix":""},{"id":515917601,"identity":"b4899d10-d4e9-4ded-af8f-1d2fdbdfb453","order_by":2,"name":"Srinivasa Rao Ummity","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABFElEQVRIie3SMUvDQBTA8RcCnc5mPZf0K1wppIuSr5IjUJcOdRFBCemSbM5v6Ie58KAuwVGULAXByeGK4BTEpKEI8aKrw/2XhLz8uBwXAJvtX+ak3dUFUMdHOxDdnfr5fjtfp6pHXAFC/EKaZfqDEYfjMobEI+Uv+wzCeX5SELtNJvOctjdsVYOXK4dWBlLJdVpkIDc0johtabopF4uKNR/GywgIh0nEXSYKHCkHYRk8Y7uXJwBiwyTsyGcSovcWXLZk8gdxsCFqn7kS+TIA3RAxQE4bguUDlx25oxj5a8y1mLFpKVMTGVcXO319dRZyr5zp6CM5Ry8udFT7vn9P9G4gh5z2IPqx7x/DVD08stlsNht8AZtYakXOdbwgAAAAAElFTkSuQmCC","orcid":"","institution":"Vellore Institute of Technology University","correspondingAuthor":true,"prefix":"","firstName":"Srinivasa","middleName":"Rao","lastName":"Ummity","suffix":""},{"id":515917602,"identity":"96ac2d8b-617d-4768-bfd8-e8515c2415be","order_by":3,"name":"Janaki Meena M","email":"","orcid":"","institution":"Vellore Institute of Technology University","correspondingAuthor":false,"prefix":"","firstName":"Janaki","middleName":"Meena","lastName":"M","suffix":""},{"id":515917603,"identity":"a8ff1d61-09a9-41e4-bdce-236f7dc8344a","order_by":4,"name":"Jayaram Balabaskaran","email":"","orcid":"","institution":"Vellore Institute of Technology University","correspondingAuthor":false,"prefix":"","firstName":"Jayaram","middleName":"","lastName":"Balabaskaran","suffix":""}],"badges":[],"createdAt":"2025-04-30 13:09:25","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6565198/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6565198/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-34084-2","type":"published","date":"2026-02-28T15:57:16+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":91816412,"identity":"c1fa7c5d-6fa7-43ce-adb0-ad9a9e43a069","added_by":"auto","created_at":"2025-09-22 06:39:59","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6978,"visible":true,"origin":"","legend":"","description":"","filename":"89db8abd417b46f5bfea8ca1e8aeec0e.json","url":"https://assets-eu.researchsquare.com/files/rs-6565198/v1/ba29baf71238d5a38b5ce6c4.json"},{"id":103765419,"identity":"adcc497f-8777-48f7-a1b5-3e411c9c669b","added_by":"auto","created_at":"2026-03-02 16:00:49","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2147331,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6565198/v1_covered_a1b6954a-3e7e-4d31-b2b9-770a14b389d6.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Computation of Sentence Similarity Score through Hybrid Deep Learning with a Special Focus on Negation Sentence.","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"semantic similarity, negation handling, conjunction handling, Siamese network, bi-directional LSTM","lastPublishedDoi":"10.21203/rs.3.rs-6565198/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6565198/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Automated answer script evaluation relies heavily on accurate sentence similarity assessment. Traditional methods often struggle with linguistic nuances, particularly negation, where misinterpretations can lead to incorrect grading and biased assessments. To address these challenges, we propose a hybrid deep learning framework designed to enhance sentence similarity detection, thereby improving the accuracy and reliability of automated evaluation systems. Our model integrates the advanced embedding capabilities of \\textbf{BERT, RoBERTa, Sentence-BERT, and Word2Vec} into a unified representation. A Siamese network with a bi-directional LSTM serves as the core computational component, enabling precise similarity scoring. This approach strengthens the model’s ability to understand negated statements and complex sentence structures. We evaluated our model on a specialized dataset containing examples of negations and conjunctions. The results demonstrated a significant improvement over existing methods, achieving an AU-ROC score of 0.984. Additionally, our model outperformed baseline approaches across Mean Absolute Error (MAE), Mean Squared Error (MSE), and R² metrics. These findings confirm the model’s effectiveness and highlight its potential for enhancing automated grading systems and other applications requiring precise interpretation of textual meaning.","manuscriptTitle":"Computation of Sentence Similarity Score through Hybrid Deep Learning with a Special Focus on Negation Sentence.","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-22 06:39:54","doi":"10.21203/rs.3.rs-6565198/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-11-24T07:12:14+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-21T17:41:20+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"152254546621071102528087854786190585805","date":"2025-11-14T08:16:52+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-23T07:57:19+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"85118196172510778037046410759498609847","date":"2025-09-16T11:39:55+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"325904167686858975439113692363047895382","date":"2025-09-14T15:28:29+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-14T11:54:54+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-08-06T17:58:41+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-05-14T11:23:19+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-13T10:52:52+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-04-30T13:01:44+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"cc3bf27b-781a-448d-85e0-491597a37e2a","owner":[],"postedDate":"September 22nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":54808770,"name":"Physical sciences/Mathematics and computing/Computational science"},{"id":54808771,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":54808772,"name":"Physical sciences/Mathematics and computing/Information technology"},{"id":54808773,"name":"Physical sciences/Mathematics and computing/Scientific data"}],"tags":[],"updatedAt":"2026-03-02T16:00:09+00:00","versionOfRecord":{"articleIdentity":"rs-6565198","link":"https://doi.org/10.1038/s41598-025-34084-2","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2026-02-28 15:57:16","publishedOnDateReadable":"February 28th, 2026"},"versionCreatedAt":"2025-09-22 06:39:54","video":"","vorDoi":"10.1038/s41598-025-34084-2","vorDoiUrl":"https://doi.org/10.1038/s41598-025-34084-2","workflowStages":[]},"version":"v1","identity":"rs-6565198","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6565198","identity":"rs-6565198","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}