Matches in SemOpenAlex for { <https://semopenalex.org/work/W4207078300> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4207078300 endingPage "11956" @default.
- W4207078300 startingPage "11947" @default.
- W4207078300 abstract "The short text, sparse features, and the lack of training data, etc. are still the key bottlenecks that restrict the successful application of traditional text classification methods. To address these problems, we propose a Multi-head-Pooling-based Graph Convolutional Network (MP-GCN) for semi-supervised short text classification, and introduce its three architectures, which focus on the node representation learning of 1-order, 1&2-order of isomorphic graphs, and 1-order of heterogeneous graphs, respectively. It only focuses on the structural information of the text graph and does not need pre-training word embedding as the initial node feature. A graph pooling based on self-attention is introduced to evaluate and select important nodes, and the multi-head method is used to provide multiple representation subspaces for pooling without adding trainable parameters. Experimental results demonstrated that, without using pre-training embedding, MP-GCN outperforms state-of-the-art models across five benchmark datasets." @default.
- W4207078300 created "2022-01-26" @default.
- W4207078300 creator A5007121753 @default.
- W4207078300 creator A5009994877 @default.
- W4207078300 creator A5074828414 @default.
- W4207078300 date "2022-01-01" @default.
- W4207078300 modified "2023-09-30" @default.
- W4207078300 title "Graph Convolutional Network Based on Multi-Head Pooling for Short Text Classification" @default.
- W4207078300 cites W1832693441 @default.
- W4207078300 cites W2120615054 @default.
- W4207078300 cites W2250539671 @default.
- W4207078300 cites W2741040846 @default.
- W4207078300 cites W2788667846 @default.
- W4207078300 cites W2892094955 @default.
- W4207078300 cites W2911286998 @default.
- W4207078300 cites W2912351236 @default.
- W4207078300 cites W2946794439 @default.
- W4207078300 cites W2950784811 @default.
- W4207078300 cites W2962946486 @default.
- W4207078300 cites W2963066159 @default.
- W4207078300 cites W2963626623 @default.
- W4207078300 cites W2963912736 @default.
- W4207078300 cites W2964173876 @default.
- W4207078300 cites W2964301648 @default.
- W4207078300 cites W2966841471 @default.
- W4207078300 cites W2970183009 @default.
- W4207078300 cites W2970398671 @default.
- W4207078300 cites W2971220558 @default.
- W4207078300 cites W2997162759 @default.
- W4207078300 cites W2997848713 @default.
- W4207078300 cites W3003393086 @default.
- W4207078300 cites W3101233295 @default.
- W4207078300 cites W3173753074 @default.
- W4207078300 cites W4210257598 @default.
- W4207078300 doi "https://doi.org/10.1109/access.2022.3146303" @default.
- W4207078300 hasPublicationYear "2022" @default.
- W4207078300 type Work @default.
- W4207078300 citedByCount "8" @default.
- W4207078300 countsByYear W42070783002022 @default.
- W4207078300 countsByYear W42070783002023 @default.
- W4207078300 crossrefType "journal-article" @default.
- W4207078300 hasAuthorship W4207078300A5007121753 @default.
- W4207078300 hasAuthorship W4207078300A5009994877 @default.
- W4207078300 hasAuthorship W4207078300A5074828414 @default.
- W4207078300 hasBestOaLocation W42070783001 @default.
- W4207078300 hasConcept C119857082 @default.
- W4207078300 hasConcept C132525143 @default.
- W4207078300 hasConcept C153180895 @default.
- W4207078300 hasConcept C154945302 @default.
- W4207078300 hasConcept C41008148 @default.
- W4207078300 hasConcept C41608201 @default.
- W4207078300 hasConcept C59404180 @default.
- W4207078300 hasConcept C70437156 @default.
- W4207078300 hasConcept C80444323 @default.
- W4207078300 hasConcept C81363708 @default.
- W4207078300 hasConceptScore W4207078300C119857082 @default.
- W4207078300 hasConceptScore W4207078300C132525143 @default.
- W4207078300 hasConceptScore W4207078300C153180895 @default.
- W4207078300 hasConceptScore W4207078300C154945302 @default.
- W4207078300 hasConceptScore W4207078300C41008148 @default.
- W4207078300 hasConceptScore W4207078300C41608201 @default.
- W4207078300 hasConceptScore W4207078300C59404180 @default.
- W4207078300 hasConceptScore W4207078300C70437156 @default.
- W4207078300 hasConceptScore W4207078300C80444323 @default.
- W4207078300 hasConceptScore W4207078300C81363708 @default.
- W4207078300 hasLocation W42070783001 @default.
- W4207078300 hasLocation W42070783002 @default.
- W4207078300 hasOpenAccess W4207078300 @default.
- W4207078300 hasPrimaryLocation W42070783001 @default.
- W4207078300 hasRelatedWork W2291847203 @default.
- W4207078300 hasRelatedWork W2424871898 @default.
- W4207078300 hasRelatedWork W2517027266 @default.
- W4207078300 hasRelatedWork W2756241593 @default.
- W4207078300 hasRelatedWork W2944724518 @default.
- W4207078300 hasRelatedWork W3004532561 @default.
- W4207078300 hasRelatedWork W3035116611 @default.
- W4207078300 hasRelatedWork W3094605108 @default.
- W4207078300 hasRelatedWork W4287763734 @default.
- W4207078300 hasRelatedWork W4287776258 @default.
- W4207078300 hasVolume "10" @default.
- W4207078300 isParatext "false" @default.
- W4207078300 isRetracted "false" @default.
- W4207078300 workType "article" @default.