Exploring Resourcefulness of the Paragraph for PrecedenceRetrieval in Legal Documents

Exploring Resourcefulness of the Paragraph for PrecedenceRetrieval in Legal Documents | 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 Exploring Resourcefulness of the Paragraph for PrecedenceRetrieval in Legal Documents Bhoomeendra Singh Sisodiya, Narendra Babu Unnam, P. Krishna Reddy, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4900252/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 3 You are reading this latest preprint version Abstract Developing computational methods for efficiently extracting relevant legal information to aid legalpractitioners is an active research area. In this regard, research efforts are being made to developefficient methods by leveraging different kinds of information in a legal document, such as meta-data, citations, keywords, sentences, paragraphs, etc. Similar to any text document, legal documentsare composed of paragraphs. In this paper, we have analyzed the resourcefulness of paragraph-levelinformation in capturing similarity among judgments for improving the performance of precedenceretrieval. The statistical analysis on the Supreme Court of India judgment dataset shows that theparagraph-level methods with only a few paragraph interactions could capture the similarity amongthe judgments and exhibit more discriminating power over the baseline document-level method. More-over, the comparison results on two benchmark datasets for the precedence retrieval on the Indiansupreme court judgments task show that the paragraph-level methods exhibit comparable perfor-mance with the state-of-the-art methods by utilizing only a few paragraph interactions. Overall, theresults show that paragraph-level granularity can better represent the legal document, and there is ascope to exploit them to improve the retrieval systems in the legal domain. Judgment similarity Legal Search Common law Precedence retrieval Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editor assigned by journal 24 Aug, 2024 Submission checks completed at journal 13 Aug, 2024 First submitted to journal 12 Aug, 2024 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-4900252","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":344594845,"identity":"6020aecc-4ca2-49a4-8b41-674839564bcd","order_by":0,"name":"Bhoomeendra Singh Sisodiya","email":"data:image/png;base64,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","orcid":"","institution":"International Institute of Information Technology, Hyderabad","correspondingAuthor":true,"prefix":"","firstName":"Bhoomeendra","middleName":"Singh","lastName":"Sisodiya","suffix":""},{"id":344594847,"identity":"209c20e3-0623-4be2-a0de-83c0092b88b2","order_by":1,"name":"Narendra Babu Unnam","email":"","orcid":"","institution":"International Institute of Information Technology, Hyderabad","correspondingAuthor":false,"prefix":"","firstName":"Narendra","middleName":"Babu","lastName":"Unnam","suffix":""},{"id":344594849,"identity":"daf96981-3fcc-4e3b-8a4d-c6302f3dfb62","order_by":2,"name":"P. Krishna Reddy","email":"","orcid":"","institution":"International Institute of Information Technology, Hyderabad","correspondingAuthor":false,"prefix":"","firstName":"P.","middleName":"Krishna","lastName":"Reddy","suffix":""},{"id":344594850,"identity":"c8d930e0-45f0-4daa-97d7-be340fcaea27","order_by":3,"name":"K.V.K. Santhy","email":"","orcid":"","institution":"Nalsar University of Law","correspondingAuthor":false,"prefix":"","firstName":"K.V.K.","middleName":"","lastName":"Santhy","suffix":""}],"badges":[],"createdAt":"2024-08-12 11:48:59","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4900252/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4900252/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":64220311,"identity":"178741d5-41a0-498a-94f8-618b502d3eef","added_by":"auto","created_at":"2024-09-10 11:22:38","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":468359,"visible":true,"origin":"","legend":"","description":"","filename":"JDSAJournalPaperPrecedenceRetreivalPaper1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4900252/v1_covered_7047a4ec-b9f0-489d-945f-6e5210173ea9.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Exploring Resourcefulness of the Paragraph for PrecedenceRetrieval in Legal Documents","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":"Judgment similarity, Legal Search, Common law, Precedence retrieval","lastPublishedDoi":"10.21203/rs.3.rs-4900252/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4900252/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Developing computational methods for efficiently extracting relevant legal information to aid legalpractitioners is an active research area. In this regard, research efforts are being made to developefficient methods by leveraging different kinds of information in a legal document, such as meta-data, citations, keywords, sentences, paragraphs, etc. Similar to any text document, legal documentsare composed of paragraphs. In this paper, we have analyzed the resourcefulness of paragraph-levelinformation in capturing similarity among judgments for improving the performance of precedenceretrieval. The statistical analysis on the Supreme Court of India judgment dataset shows that theparagraph-level methods with only a few paragraph interactions could capture the similarity amongthe judgments and exhibit more discriminating power over the baseline document-level method. More-over, the comparison results on two benchmark datasets for the precedence retrieval on the Indiansupreme court judgments task show that the paragraph-level methods exhibit comparable perfor-mance with the state-of-the-art methods by utilizing only a few paragraph interactions. Overall, theresults show that paragraph-level granularity can better represent the legal document, and there is ascope to exploit them to improve the retrieval systems in the legal domain.","manuscriptTitle":"Exploring Resourcefulness of the Paragraph for PrecedenceRetrieval in Legal Documents","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-09-10 11:22:28","doi":"10.21203/rs.3.rs-4900252/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorAssigned","content":"","date":"2024-08-24T15:15:37+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-08-13T07:58:07+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal of Data Science and Analytics","date":"2024-08-12T11:47:07+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":"9366349c-4c09-49f1-a354-e281bf6bc6c2","owner":[],"postedDate":"September 10th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2024-09-10T11:22:29+00:00","versionOfRecord":[],"versionCreatedAt":"2024-09-10 11:22:28","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4900252","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4900252","identity":"rs-4900252","version":["v1"]},"buildId":"_2-kVJe1T_tPrBINL-cwx","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}