Multi-task Dual-Graph Network framework for Aspect Sentiment Triplet Extraction

Multi-task Dual-Graph Network framework for Aspect Sentiment Triplet Extraction | 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 Multi-task Dual-Graph Network framework for Aspect Sentiment Triplet Extraction Liuxuan Wang, Yanqian Zheng, Mingwei Tang, Kezhu Meng, Mingfeng Zhao, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4216499/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 Aspect Sentiment Triplet Extraction is a task that extracts aspects, opinion words corresponding to aspects and sentiment polarity from review sentences. Although aspect emotion triple extraction technology has achieved remarkable results in recent years, it still has a few drawbacks. Many existing research methods ignore important issues, such as the dependency relationships between emotional triad elements and the detection of aspect and viewpoint boundary terms at the phrase-level. Due to the above problems, this paper proposes a multi-task joint learning architecture based on dual graph networks (DGNMT). Firstly, a shared sentence encoder module is proposed in the model. The middle-layer and top-level feature representations of the BERT encoder are applied to two different subtasks in this module. Secondly, Dual-Graph Network Learning module has been designed. As part of the dual-graph network learning layer, this module introduces a graph attention network based on phrase structure trees in the joint extraction task branch. For the triple extraction task branch, a graph convolution network is used based on the modified syntactic dependency graph in order to determine the syntactic relationships between triple elements. Additionally , the Multi-Task Tagging module is proposed to extract labels for tasks as well as triplet extraction tasks. And then, predictions are made based on 1D sequence tags and 2D word pair matrices, and the tag information of the two tasks is transformed into each other through a conversion strategy. According to the final experimental results, the model outperforms a state-of-the-art baseline model on four commonly used evaluation indicators. Aspect Sentiment Triplet Extraction Shared Sentence Encoder Dual-Graph Network Learning Multi-Task Tagging 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-4216499","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":287453235,"identity":"3542a479-4b17-44c9-b9fb-6592abfecf66","order_by":0,"name":"Liuxuan Wang","email":"","orcid":"","institution":"Xihua University","correspondingAuthor":false,"prefix":"","firstName":"Liuxuan","middleName":"","lastName":"Wang","suffix":""},{"id":287453236,"identity":"9cef5d43-3495-4626-b95e-27422555fc17","order_by":1,"name":"Yanqian Zheng","email":"","orcid":"","institution":"Xihua University","correspondingAuthor":false,"prefix":"","firstName":"Yanqian","middleName":"","lastName":"Zheng","suffix":""},{"id":287453237,"identity":"8e8c76a3-026d-4f8d-adad-b2dc2cd94a7a","order_by":2,"name":"Mingwei Tang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAyUlEQVRIiWNgGAWjYLACCR6Jen5m5oMPiFLNAyIsZCwSJNvZkg2I11JhU5FgcJ7HTIAoLfbsZw+/uJEjkWd8mMGMgaHGJpqwLTx5aZYzzkgUmx1mSHvAcCwtt4Gww3LMjCV7JBi3HWY4bsDYcJgILfxvzIz//pNg3NzM2CZBnBaJHOMHwEBO3MDMzEaklhtvzEDxYixxmI3ZIIEYv7D35xh/kOCpk+PvP//xwYcaG8JagIBNAs5MIEI5CDB/IFLhKBgFo2AUjFQAABM4OPn3Wkk1AAAAAElFTkSuQmCC","orcid":"","institution":"Xihua University","correspondingAuthor":true,"prefix":"","firstName":"Mingwei","middleName":"","lastName":"Tang","suffix":""},{"id":287453238,"identity":"4542cc9a-d2f1-4c0a-bd11-b5494622b3a8","order_by":3,"name":"Kezhu Meng","email":"","orcid":"","institution":"Xihua University","correspondingAuthor":false,"prefix":"","firstName":"Kezhu","middleName":"","lastName":"Meng","suffix":""},{"id":287453239,"identity":"e43fdddf-e7c5-4119-8a3b-061124206ee5","order_by":4,"name":"Mingfeng Zhao","email":"","orcid":"","institution":"China Mobile Group Design Institute Co., Ltd. Sichuan Branch","correspondingAuthor":false,"prefix":"","firstName":"Mingfeng","middleName":"","lastName":"Zhao","suffix":""},{"id":287453240,"identity":"59265674-4087-4993-8fe1-295ac6b160c6","order_by":5,"name":"Wei Zhou","email":"","orcid":"","institution":"Xihua University","correspondingAuthor":false,"prefix":"","firstName":"Wei","middleName":"","lastName":"Zhou","suffix":""}],"badges":[],"createdAt":"2024-04-04 08:22:39","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4216499/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4216499/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":57751306,"identity":"c40cf150-5796-4ebf-8456-60f8aa0d0f37","added_by":"auto","created_at":"2024-06-05 07:11:29","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":493994,"visible":true,"origin":"","legend":"","description":"","filename":"templateArticle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4216499/v1_covered_a5fa6290-85f8-40dd-ae99-792fbd572279.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Multi-task Dual-Graph Network framework for Aspect Sentiment Triplet Extraction","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":"Aspect Sentiment Triplet Extraction, Shared Sentence Encoder, Dual-Graph Network Learning, Multi-Task Tagging","lastPublishedDoi":"10.21203/rs.3.rs-4216499/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4216499/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Aspect Sentiment Triplet Extraction is a task that extracts aspects, opinion words corresponding to aspects and sentiment polarity from review sentences. Although aspect emotion triple extraction technology has achieved remarkable results in recent years, it still has a few drawbacks. Many existing research methods ignore important issues, such as the dependency relationships between emotional triad elements and the detection of aspect and viewpoint boundary terms at the phrase-level. Due to the above problems, this paper proposes a multi-task joint learning architecture based on dual graph networks (DGNMT). Firstly, a shared sentence encoder module is proposed in the model. The middle-layer and top-level feature representations of the BERT encoder are applied to two different subtasks in this module. Secondly, Dual-Graph Network Learning module has been designed. As part of the dual-graph network learning layer, this module introduces a graph attention network based on phrase structure trees in the joint extraction task branch. For the triple extraction task branch, a graph convolution network is used based on the modified syntactic dependency graph in order to determine the syntactic relationships between triple elements. Additionally , the Multi-Task Tagging module is proposed to extract labels for tasks as well as triplet extraction tasks. And then, predictions are made based on 1D sequence tags and 2D word pair matrices, and the tag information of the two tasks is transformed into each other through a conversion strategy. According to the final experimental results, the model outperforms a state-of-the-art baseline model on four commonly used evaluation indicators.","manuscriptTitle":"Multi-task Dual-Graph Network framework for Aspect Sentiment Triplet Extraction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-09 17:38:41","doi":"10.21203/rs.3.rs-4216499/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":"7c139449-ef05-4e7b-88f9-ce1544191dd0","owner":[],"postedDate":"April 9th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-06-05T07:03:22+00:00","versionOfRecord":[],"versionCreatedAt":"2024-04-09 17:38:41","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4216499","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4216499","identity":"rs-4216499","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}