FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4280641716> ?p ?o ?g. }

• W4280641716 endingPage "18" @default.
• W4280641716 startingPage "1" @default.
• W4280641716 abstract "Structured text with plentiful hierarchical structure information is an important part in real-world complex texts. Structured text classification is attracting more attention in natural language processing due to the increasing complexity of application scenarios. Most existing methods treat structured text from a local hierarchy perspective, focusing on the semantics dependency and the graph structure of the structured text independently. However, structured text has global hierarchical structures with sophisticated dependency when compared to unstructured text. According to the variety of structured texts, it is not appropriate to use the existing methods directly. The function of distinction information within semantics dependency and graph structure for structured text, referred to as meta-information, should be stated more precisely. In this article, we propose HGMETA, a novel meta-information embedding frame network for structured text classification, to obtain the fusion embedding of hierarchical semantics dependency and graph structure in a structured text, and to distill the meta-information from fusion characteristics. To integrate the global hierarchical features with fused structured text information, we design a hierarchical LDA module and a structured text embedding module. Specially, we employ a multi-hop message passing mechanism to explicitly incorporate complex dependency into a meta-graph. The meta-information is constructed from meta-graph via neighborhood-based propagation to distill redundant information. Furthermore, using an attention-based network, we investigate the complementarity of semantics dependency and graph structure based on global hierarchical characteristics and meta-information. Finally, the fusion embedding and the meta-information can be straightforwardly incorporated for structured text classification. Experiments conducted on three real-world datasets show the effectiveness of meta-information and demonstrate the superiority of our method." @default.
• W4280641716 created "2022-05-22" @default.
• W4280641716 creator A5008961177 @default.
• W4280641716 creator A5010302081 @default.
• W4280641716 creator A5037095246 @default.
• W4280641716 date "2023-02-20" @default.
• W4280641716 modified "2023-09-24" @default.
• W4280641716 title "Meta-Information Fusion of Hierarchical Semantics Dependency and Graph Structure for Structured Text Classification" @default.
• W4280641716 cites W179875071 @default.
• W4280641716 cites W1832693441 @default.
• W4280641716 cites W2121082043 @default.
• W4280641716 cites W2155529673 @default.
• W4280641716 cites W2250539671 @default.
• W4280641716 cites W2250662230 @default.
• W4280641716 cites W2470673105 @default.
• W4280641716 cites W2591922431 @default.
• W4280641716 cites W2767210791 @default.
• W4280641716 cites W2785128315 @default.
• W4280641716 cites W2954148014 @default.
• W4280641716 cites W2962946486 @default.
• W4280641716 cites W2963224980 @default.
• W4280641716 cites W2963270153 @default.
• W4280641716 cites W2970183009 @default.
• W4280641716 cites W2979450518 @default.
• W4280641716 cites W2996899616 @default.
• W4280641716 cites W2998436975 @default.
• W4280641716 cites W3034892514 @default.
• W4280641716 cites W3035568641 @default.
• W4280641716 cites W3152368098 @default.
• W4280641716 cites W3159597990 @default.
• W4280641716 cites W3161789553 @default.
• W4280641716 doi "https://doi.org/10.1145/3537971" @default.
• W4280641716 hasPublicationYear "2023" @default.
• W4280641716 type Work @default.
• W4280641716 citedByCount "1" @default.
• W4280641716 countsByYear W42806417162022 @default.
• W4280641716 crossrefType "journal-article" @default.
• W4280641716 hasAuthorship W4280641716A5008961177 @default.
• W4280641716 hasAuthorship W4280641716A5010302081 @default.
• W4280641716 hasAuthorship W4280641716A5037095246 @default.
• W4280641716 hasConcept C132525143 @default.
• W4280641716 hasConcept C154945302 @default.
• W4280641716 hasConcept C16311509 @default.
• W4280641716 hasConcept C19768560 @default.
• W4280641716 hasConcept C204321447 @default.
• W4280641716 hasConcept C23123220 @default.
• W4280641716 hasConcept C41008148 @default.
• W4280641716 hasConcept C41608201 @default.
• W4280641716 hasConcept C80444323 @default.
• W4280641716 hasConceptScore W4280641716C132525143 @default.
• W4280641716 hasConceptScore W4280641716C154945302 @default.
• W4280641716 hasConceptScore W4280641716C16311509 @default.
• W4280641716 hasConceptScore W4280641716C19768560 @default.
• W4280641716 hasConceptScore W4280641716C204321447 @default.
• W4280641716 hasConceptScore W4280641716C23123220 @default.
• W4280641716 hasConceptScore W4280641716C41008148 @default.
• W4280641716 hasConceptScore W4280641716C41608201 @default.
• W4280641716 hasConceptScore W4280641716C80444323 @default.
• W4280641716 hasFunder F4320321001 @default.
• W4280641716 hasIssue "2" @default.
• W4280641716 hasLocation W42806417161 @default.
• W4280641716 hasOpenAccess W4280641716 @default.
• W4280641716 hasPrimaryLocation W42806417161 @default.
• W4280641716 hasRelatedWork W1483367581 @default.
• W4280641716 hasRelatedWork W2131662294 @default.
• W4280641716 hasRelatedWork W2200456380 @default.
• W4280641716 hasRelatedWork W2369797701 @default.
• W4280641716 hasRelatedWork W2379773790 @default.
• W4280641716 hasRelatedWork W2381168281 @default.
• W4280641716 hasRelatedWork W2430210575 @default.
• W4280641716 hasRelatedWork W2511797247 @default.
• W4280641716 hasRelatedWork W3200266554 @default.
• W4280641716 hasRelatedWork W3210155192 @default.
• W4280641716 hasVolume "17" @default.
• W4280641716 isParatext "false" @default.
• W4280641716 isRetracted "false" @default.
• W4280641716 workType "article" @default.