Diversity question generation based on contrastive search algorithm

Diversity question generation based on contrastive search algorithm | 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 Diversity question generation based on contrastive search algorithm Mingtao Zhou, Juxiang Zhou, Jianhou Gan, Jun Wang, Mingjie Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3887342/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 Diversity question generation (DQG) is an extremely challenging task, involving the generation of questions of multiple answerable and diverse vocabulary based on given contextual information and answers. Despite notable advancements in prior research, this field encounters two primary challenges: (i) there is a locality of DQG, with a lack of dedicated datasets specifically designed for sentence-level diversity question generation (SL-DQG); (ii) the decoding process often leads to issues such as word repetition, affecting the answerability of the generated questions. To address these challenges, we extract sentences containing answers from paragraphs in a paragraph-level diversity question generation (PL-DQG) dataset, constructing a dataset for SL-DQG. Then, we propose a diversity question generation model based on a contrastive search algorithm (DQG-CSA), exploring both SL-DQG and PL-DQG. Our model fine-tunes a pre-trained language model for downstream tasks, directly generating copious semantically similar and lexically diverse questions. Furthermore, we introduces a contrastive search decoding method to address word repetition issues in both SL-DQG and PL-DQG, enhancing the answerability of the generated questions. Experimental results demonstrate that incorporating the contrastive search algorithm in diversity studies at both sentence and paragraph levels, outperforms other decoding methods. And achieving a balance between answerability, fluency, and semantic similarity. Diversity question generation Contrastive search Answerability Paragraph-level Sentence-level 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-3887342","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":269354927,"identity":"ef87fe50-54b0-4a3a-b451-f01490366af5","order_by":0,"name":"Mingtao Zhou","email":"","orcid":"","institution":"Yunnan Normal University","correspondingAuthor":false,"prefix":"","firstName":"Mingtao","middleName":"","lastName":"Zhou","suffix":""},{"id":269354928,"identity":"5a9d4366-20bd-4d9d-acf1-a8603c13842b","order_by":1,"name":"Juxiang Zhou","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzElEQVRIiWNgGAWjYFCCAwwMCUCKn5n54APStEi2syUbkGaZwXkeMwGiVMo3njGTeFBzx27zYQYzBoYam2iCWhgbzhgbJBx7lrztMEPaA4ZjabkNhLQwM5wxfJDAdjjZ7DDDcQPGhsOEtbAxnDE4kPDvcLJxM2ObBFFaeEC2JLYdtjNgZmYjTosEw7Fig8S+wwkSh9mYgZ4iwi/yMw5vk/zx7bA9f//5jw8+1NgQ1sIgcQBMJYJVJhBUDgL8EFPtiVI8CkbBKBgFIxMAAJIyQSny1dRuAAAAAElFTkSuQmCC","orcid":"","institution":"Yunnan Normal University","correspondingAuthor":true,"prefix":"","firstName":"Juxiang","middleName":"","lastName":"Zhou","suffix":""},{"id":269354929,"identity":"55ad7276-e49b-4944-a258-2657e614a17f","order_by":2,"name":"Jianhou Gan","email":"","orcid":"","institution":"Yunnan Normal University","correspondingAuthor":false,"prefix":"","firstName":"Jianhou","middleName":"","lastName":"Gan","suffix":""},{"id":269354930,"identity":"821dcdc8-641d-497c-9f38-179cc5e7fdbe","order_by":3,"name":"Jun Wang","email":"","orcid":"","institution":"Yunnan Normal University","correspondingAuthor":false,"prefix":"","firstName":"Jun","middleName":"","lastName":"Wang","suffix":""},{"id":269354931,"identity":"97494f96-d5ad-4e06-b6aa-ff3bf0da4c9a","order_by":4,"name":"Mingjie Wang","email":"","orcid":"","institution":"Yunnan Normal University","correspondingAuthor":false,"prefix":"","firstName":"Mingjie","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2024-01-22 08:18:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3887342/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3887342/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":52873004,"identity":"e3367333-ab19-4c4e-96e0-6aa7d753e5fb","added_by":"auto","created_at":"2024-03-18 07:35:19","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1196110,"visible":true,"origin":"","legend":"","description":"","filename":"snarticletemplate.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3887342/v1_covered_c8c49147-a8d3-4968-89ba-df0abc707c48.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Diversity question generation based on contrastive search algorithm","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":"Diversity question generation, Contrastive search, Answerability, Paragraph-level, Sentence-level","lastPublishedDoi":"10.21203/rs.3.rs-3887342/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3887342/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Diversity question generation (DQG) is an extremely challenging task, involving the generation of questions of multiple answerable and diverse vocabulary based on given contextual information and answers. Despite notable advancements in prior research, this field encounters two primary challenges: (i) there is a locality of DQG, with a lack of dedicated datasets specifically designed for sentence-level diversity question generation (SL-DQG); (ii) the decoding process often leads to issues such as word repetition, affecting the answerability of the generated questions. To address these challenges, we extract sentences containing answers from paragraphs in a paragraph-level diversity question generation (PL-DQG) dataset, constructing a dataset for SL-DQG. Then, we propose a diversity question generation model based on a contrastive search algorithm (DQG-CSA), exploring both SL-DQG and PL-DQG. Our model fine-tunes a pre-trained language model for downstream tasks, directly generating copious semantically similar and lexically diverse questions. Furthermore, we introduces a contrastive search decoding method to address word repetition issues in both SL-DQG and PL-DQG, enhancing the answerability of the generated questions. Experimental results demonstrate that incorporating the contrastive search algorithm in diversity studies at both sentence and paragraph levels, outperforms other decoding methods. And achieving a balance between answerability, fluency, and semantic similarity.","manuscriptTitle":"Diversity question generation based on contrastive search algorithm","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-01-30 10:16:28","doi":"10.21203/rs.3.rs-3887342/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":"4d503540-ab1d-40e1-8a57-cdd9ff87222d","owner":[],"postedDate":"January 30th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-03-18T07:27:08+00:00","versionOfRecord":[],"versionCreatedAt":"2024-01-30 10:16:28","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3887342","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3887342","identity":"rs-3887342","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}