FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3006271038> ?p ?o ?g. }

• W3006271038 endingPage "30896" @default.
• W3006271038 startingPage "30885" @default.
• W3006271038 abstract "Traditional methods of multi-label text classification, particularly deep learning, have achieved remarkable results. However, most of these methods use word2vec technology to represent sequential text information, while ignoring the logic and internal hierarchy of the text itself. Although these approaches can learn the hypothetical hierarchy and logic of the text, it is unexplained. In addition, the traditional approach treats labels as independent individuals and ignores the relationships between them, which not only does not reflect reality but also causes significant loss of semantic information. In this paper, we propose a novel Hierarchical Graph Transformer based deep learning model for large-scale multi-label text classification. We first model the text into a graph structure that can embody the different semantics of the text and the connections between them. We then use a multi-layer transformer structure with a multi-head attention mechanism at the word, sentence, and graph levels to fully capture the features of the text and observe the importance of the separate parts. Finally, we use the hierarchical relationship of the labels to generate the representation of the labels, and design a weighted loss function based on the semantic distances of the labels. Extensive experiments conducted on three benchmark datasets demonstrated that the proposed model can realistically capture the hierarchy and logic of text and improve performance compared with the state-of-the-art methods." @default.
• W3006271038 created "2020-02-24" @default.
• W3006271038 creator A5019876087 @default.
• W3006271038 creator A5031608916 @default.
• W3006271038 creator A5032507421 @default.
• W3006271038 creator A5036307171 @default.
• W3006271038 creator A5040684540 @default.
• W3006271038 creator A5046380471 @default.
• W3006271038 creator A5055566607 @default.
• W3006271038 creator A5086666436 @default.
• W3006271038 creator A5088153231 @default.
• W3006271038 creator A5089997723 @default.
• W3006271038 date "2020-01-01" @default.
• W3006271038 modified "2023-10-16" @default.
• W3006271038 title "Hierarchical Graph Transformer-Based Deep Learning Model for Large-Scale Multi-Label Text Classification" @default.
• W3006271038 cites W1834987204 @default.
• W3006271038 cites W1971014294 @default.
• W3006271038 cites W1980867644 @default.
• W3006271038 cites W1997530783 @default.
• W3006271038 cites W2068074736 @default.
• W3006271038 cites W2101746535 @default.
• W3006271038 cites W2132311402 @default.
• W3006271038 cites W2155893237 @default.
• W3006271038 cites W2156956856 @default.
• W3006271038 cites W2157331557 @default.
• W3006271038 cites W2250539671 @default.
• W3006271038 cites W2250662230 @default.
• W3006271038 cites W2470673105 @default.
• W3006271038 cites W2508429489 @default.
• W3006271038 cites W2515248967 @default.
• W3006271038 cites W2534727297 @default.
• W3006271038 cites W2563010554 @default.
• W3006271038 cites W2618530766 @default.
• W3006271038 cites W2619706086 @default.
• W3006271038 cites W2621048556 @default.
• W3006271038 cites W2623162856 @default.
• W3006271038 cites W2739996966 @default.
• W3006271038 cites W2788125153 @default.
• W3006271038 cites W2788667846 @default.
• W3006271038 cites W2808190017 @default.
• W3006271038 cites W2891768540 @default.
• W3006271038 cites W2904265202 @default.
• W3006271038 cites W2952641483 @default.
• W3006271038 cites W2966714118 @default.
• W3006271038 cites W2966779056 @default.
• W3006271038 cites W2995837271 @default.
• W3006271038 cites W3001437801 @default.
• W3006271038 cites W4236122429 @default.
• W3006271038 cites W4254196108 @default.
• W3006271038 doi "https://doi.org/10.1109/access.2020.2972751" @default.
• W3006271038 hasPublicationYear "2020" @default.
• W3006271038 type Work @default.
• W3006271038 sameAs 3006271038 @default.
• W3006271038 citedByCount "31" @default.
• W3006271038 countsByYear W30062710382020 @default.
• W3006271038 countsByYear W30062710382021 @default.
• W3006271038 countsByYear W30062710382022 @default.
• W3006271038 countsByYear W30062710382023 @default.
• W3006271038 crossrefType "journal-article" @default.
• W3006271038 hasAuthorship W3006271038A5019876087 @default.
• W3006271038 hasAuthorship W3006271038A5031608916 @default.
• W3006271038 hasAuthorship W3006271038A5032507421 @default.
• W3006271038 hasAuthorship W3006271038A5036307171 @default.
• W3006271038 hasAuthorship W3006271038A5040684540 @default.
• W3006271038 hasAuthorship W3006271038A5046380471 @default.
• W3006271038 hasAuthorship W3006271038A5055566607 @default.
• W3006271038 hasAuthorship W3006271038A5086666436 @default.
• W3006271038 hasAuthorship W3006271038A5088153231 @default.
• W3006271038 hasAuthorship W3006271038A5089997723 @default.
• W3006271038 hasBestOaLocation W30062710381 @default.
• W3006271038 hasConcept C108583219 @default.
• W3006271038 hasConcept C119857082 @default.
• W3006271038 hasConcept C121332964 @default.
• W3006271038 hasConcept C132525143 @default.
• W3006271038 hasConcept C154945302 @default.
• W3006271038 hasConcept C162324750 @default.
• W3006271038 hasConcept C165801399 @default.
• W3006271038 hasConcept C204321447 @default.
• W3006271038 hasConcept C2776461190 @default.
• W3006271038 hasConcept C2777530160 @default.
• W3006271038 hasConcept C31170391 @default.
• W3006271038 hasConcept C34447519 @default.
• W3006271038 hasConcept C41008148 @default.
• W3006271038 hasConcept C41608201 @default.
• W3006271038 hasConcept C62520636 @default.
• W3006271038 hasConcept C66322947 @default.
• W3006271038 hasConcept C66945725 @default.
• W3006271038 hasConcept C71472368 @default.
• W3006271038 hasConcept C80444323 @default.
• W3006271038 hasConceptScore W3006271038C108583219 @default.
• W3006271038 hasConceptScore W3006271038C119857082 @default.
• W3006271038 hasConceptScore W3006271038C121332964 @default.
• W3006271038 hasConceptScore W3006271038C132525143 @default.
• W3006271038 hasConceptScore W3006271038C154945302 @default.
• W3006271038 hasConceptScore W3006271038C162324750 @default.
• W3006271038 hasConceptScore W3006271038C165801399 @default.
• W3006271038 hasConceptScore W3006271038C204321447 @default.
• W3006271038 hasConceptScore W3006271038C2776461190 @default.

• next