Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891761261> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2891761261 abstract "Text classification is an important and classical problem in natural language processing. There have been a number of studies that applied convolutional neural networks (convolution on regular grid, e.g., sequence) to classification. However, only a limited number of studies have explored the more flexible graph convolutional neural networks (convolution on non-grid, e.g., arbitrary graph) for the task. In this work, we propose to use graph convolutional networks for text classification. We build a single text graph for a corpus based on word co-occurrence and document word relations, then learn a Text Graph Convolutional Network (Text GCN) for the corpus. Our Text GCN is initialized with one-hot representation for word and document, it then jointly learns the embeddings for both words and documents, as supervised by the known class labels for documents. Our experimental results on multiple benchmark datasets demonstrate that a vanilla Text GCN without any external word embeddings or knowledge outperforms state-of-the-art methods for text classification. On the other hand, Text GCN also learns predictive word and document embeddings. In addition, experimental results show that the improvement of Text GCN over state-of-the-art comparison methods become more prominent as we lower the percentage of training data, suggesting the robustness of Text GCN to less training data in text classification." @default.
- W2891761261 created "2018-09-27" @default.
- W2891761261 creator A5014355203 @default.
- W2891761261 creator A5031637427 @default.
- W2891761261 creator A5074672910 @default.
- W2891761261 date "2018-09-15" @default.
- W2891761261 modified "2023-09-25" @default.
- W2891761261 title "Graph Convolutional Networks for Text Classification" @default.
- W2891761261 cites W2104246439 @default.
- W2891761261 cites W2124996938 @default.
- W2891761261 cites W2187089797 @default.
- W2891761261 cites W2250539671 @default.
- W2891761261 cites W2252979829 @default.
- W2891761261 cites W2566209712 @default.
- W2891761261 cites W2600702321 @default.
- W2891761261 cites W2612881151 @default.
- W2891761261 cites W2624431344 @default.
- W2891761261 cites W2726375170 @default.
- W2891761261 cites W2786915849 @default.
- W2891761261 cites W2788667846 @default.
- W2891761261 cites W2798915520 @default.
- W2891761261 cites W2805516822 @default.
- W2891761261 cites W2912503608 @default.
- W2891761261 cites W2949547296 @default.
- W2891761261 cites W2950133940 @default.
- W2891761261 cites W2952186591 @default.
- W2891761261 cites W2963224980 @default.
- W2891761261 cites W2963858333 @default.
- W2891761261 cites W2963912736 @default.
- W2891761261 cites W2964051675 @default.
- W2891761261 cites W2964121744 @default.
- W2891761261 cites W2964301648 @default.
- W2891761261 cites W2964311892 @default.
- W2891761261 cites W2964321699 @default.
- W2891761261 cites W3104717349 @default.
- W2891761261 cites W637153065 @default.
- W2891761261 doi "https://doi.org/10.48550/arxiv.1809.05679" @default.
- W2891761261 hasPublicationYear "2018" @default.
- W2891761261 type Work @default.
- W2891761261 sameAs 2891761261 @default.
- W2891761261 citedByCount "18" @default.
- W2891761261 countsByYear W28917612612018 @default.
- W2891761261 countsByYear W28917612612019 @default.
- W2891761261 countsByYear W28917612612020 @default.
- W2891761261 countsByYear W28917612612021 @default.
- W2891761261 crossrefType "posted-content" @default.
- W2891761261 hasAuthorship W2891761261A5014355203 @default.
- W2891761261 hasAuthorship W2891761261A5031637427 @default.
- W2891761261 hasAuthorship W2891761261A5074672910 @default.
- W2891761261 hasBestOaLocation W28917612611 @default.
- W2891761261 hasConcept C132525143 @default.
- W2891761261 hasConcept C153180895 @default.
- W2891761261 hasConcept C154945302 @default.
- W2891761261 hasConcept C204321447 @default.
- W2891761261 hasConcept C2524010 @default.
- W2891761261 hasConcept C33923547 @default.
- W2891761261 hasConcept C41008148 @default.
- W2891761261 hasConcept C66945725 @default.
- W2891761261 hasConcept C71472368 @default.
- W2891761261 hasConcept C80444323 @default.
- W2891761261 hasConcept C81363708 @default.
- W2891761261 hasConcept C90805587 @default.
- W2891761261 hasConceptScore W2891761261C132525143 @default.
- W2891761261 hasConceptScore W2891761261C153180895 @default.
- W2891761261 hasConceptScore W2891761261C154945302 @default.
- W2891761261 hasConceptScore W2891761261C204321447 @default.
- W2891761261 hasConceptScore W2891761261C2524010 @default.
- W2891761261 hasConceptScore W2891761261C33923547 @default.
- W2891761261 hasConceptScore W2891761261C41008148 @default.
- W2891761261 hasConceptScore W2891761261C66945725 @default.
- W2891761261 hasConceptScore W2891761261C71472368 @default.
- W2891761261 hasConceptScore W2891761261C80444323 @default.
- W2891761261 hasConceptScore W2891761261C81363708 @default.
- W2891761261 hasConceptScore W2891761261C90805587 @default.
- W2891761261 hasLocation W28917612611 @default.
- W2891761261 hasOpenAccess W2891761261 @default.
- W2891761261 hasPrimaryLocation W28917612611 @default.
- W2891761261 hasRelatedWork W2175746458 @default.
- W2891761261 hasRelatedWork W2613736958 @default.
- W2891761261 hasRelatedWork W2732542196 @default.
- W2891761261 hasRelatedWork W2738221750 @default.
- W2891761261 hasRelatedWork W2760085659 @default.
- W2891761261 hasRelatedWork W2912288872 @default.
- W2891761261 hasRelatedWork W3012978760 @default.
- W2891761261 hasRelatedWork W3081496756 @default.
- W2891761261 hasRelatedWork W3093612317 @default.
- W2891761261 hasRelatedWork W3107474891 @default.
- W2891761261 isParatext "false" @default.
- W2891761261 isRetracted "false" @default.
- W2891761261 magId "2891761261" @default.
- W2891761261 workType "article" @default.