A Gated Graph Neural Network With Attention for Text Classification Based on Coupled P Systems
Text classification is a classical task in natural language processing. Prior traditional text classification methods rely on manually extracted features to a great extent, which are easily influenced by human subjectivity. Some existing text classification methods based on the artificial neural net...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10184018/ |
| _version_ | 1797774905177014272 |
|---|---|
| author | Jiaqi Zhang Xiyu Liu |
| author_facet | Jiaqi Zhang Xiyu Liu |
| author_sort | Jiaqi Zhang |
| collection | DOAJ |
| description | Text classification is a classical task in natural language processing. Prior traditional text classification methods rely on manually extracted features to a great extent, which are easily influenced by human subjectivity. Some existing text classification methods based on the artificial neural networks sometimes neglect the contextual semantic relationships of discontinuous word sequences, resulting in poor learning results. To alleviate these problems, we propose an attention-based gated graph neural network in the framework of coupled P systems (CPGANN) to automatically extract feature representations of nodes. The gating unit with attention is introduced to aggregate neighbor information to capture context semantic relations, and effectively alleviate the long-term dependence on discontinuous words. In order to obtain more discriminative nodes for classification, the attention mechanism is employed in CPGANN to extract keyword nodes before readout to aggregate subgraph representations. Extensive experiments on four real-world datasets demonstrate that CPGANN outperforms all other state-of-the-art baseline algorithms. |
| first_indexed | 2024-03-12T22:27:57Z |
| format | Article |
| id | doaj.art-bc671cc111d0452da8b84526a762c77f |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-12T22:27:57Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-bc671cc111d0452da8b84526a762c77f2023-07-21T23:01:19ZengIEEEIEEE Access2169-35362023-01-0111724487246110.1109/ACCESS.2023.329557210184018A Gated Graph Neural Network With Attention for Text Classification Based on Coupled P SystemsJiaqi Zhang0https://orcid.org/0009-0007-2744-0902Xiyu Liu1https://orcid.org/0000-0003-4976-9227Business School, Shandong Normal University, Jinan, ChinaBusiness School, Shandong Normal University, Jinan, ChinaText classification is a classical task in natural language processing. Prior traditional text classification methods rely on manually extracted features to a great extent, which are easily influenced by human subjectivity. Some existing text classification methods based on the artificial neural networks sometimes neglect the contextual semantic relationships of discontinuous word sequences, resulting in poor learning results. To alleviate these problems, we propose an attention-based gated graph neural network in the framework of coupled P systems (CPGANN) to automatically extract feature representations of nodes. The gating unit with attention is introduced to aggregate neighbor information to capture context semantic relations, and effectively alleviate the long-term dependence on discontinuous words. In order to obtain more discriminative nodes for classification, the attention mechanism is employed in CPGANN to extract keyword nodes before readout to aggregate subgraph representations. Extensive experiments on four real-world datasets demonstrate that CPGANN outperforms all other state-of-the-art baseline algorithms.https://ieeexplore.ieee.org/document/10184018/Attention mechanismgraph neural networkP systemstext classification |
| spellingShingle | Jiaqi Zhang Xiyu Liu A Gated Graph Neural Network With Attention for Text Classification Based on Coupled P Systems IEEE Access Attention mechanism graph neural network P systems text classification |
| title | A Gated Graph Neural Network With Attention for Text Classification Based on Coupled P Systems |
| title_full | A Gated Graph Neural Network With Attention for Text Classification Based on Coupled P Systems |
| title_fullStr | A Gated Graph Neural Network With Attention for Text Classification Based on Coupled P Systems |
| title_full_unstemmed | A Gated Graph Neural Network With Attention for Text Classification Based on Coupled P Systems |
| title_short | A Gated Graph Neural Network With Attention for Text Classification Based on Coupled P Systems |
| title_sort | gated graph neural network with attention for text classification based on coupled p systems |
| topic | Attention mechanism graph neural network P systems text classification |
| url | https://ieeexplore.ieee.org/document/10184018/ |
| work_keys_str_mv | AT jiaqizhang agatedgraphneuralnetworkwithattentionfortextclassificationbasedoncoupledpsystems AT xiyuliu agatedgraphneuralnetworkwithattentionfortextclassificationbasedoncoupledpsystems AT jiaqizhang gatedgraphneuralnetworkwithattentionfortextclassificationbasedoncoupledpsystems AT xiyuliu gatedgraphneuralnetworkwithattentionfortextclassificationbasedoncoupledpsystems |