DCAT: Combining Multisemantic Dual-Channel Attention Fusion for Text Classification
Authors: 
Kaifang Dong, Yifan Liu, Fuyong Xu, Peiyu LiuAuthors Info & Claims
Kaifang Dong, Yifan Liu, Fuyong Xu, Peiyu LiuAuthors Info & ClaimsAbstract
Text classification is a fundamental and central position in natural language processing. There are many solutions to the text classification problem, but few use the semantic combination of multiple perspectives to improve the classification performance. This article proposes a dual-channel attention network model called DCAT, which uses the complementarity between semantics to refine the understanding deficit. Specifically, DCAT first captures the logical semantics of the text through transductive learning and graph structure. Then, at the attention fusion layer (channel), we use logical semantics to perform joint semantic training on other semantics to correct the predictions of unlabeled test data incrementally. Experiments show that DCAT can achieve more accurate classification on a wide range of text classification datasets, which is vital for subsequent text mining tasks.
References
[1]
E. Cambria, “Affective computing and sentiment analysis,” IEEE Intell. Syst., vol. 31, no. 2, pp. 102–107, Mar./Apr. 2016.
[2]
S. Bandyopadhyay, D. Das, N. Howard, A. Hussain, A. Gelbukh, and S. Poria, “Enhanced SenticNet with affective labels for concept-based opinion mining,” IEEE Intell. Syst., vol. 28, no. 2, pp. 31–38, Mar./Apr. 2013.
[3]
C. Xu, B. Su, Y. Cheng, W. Pan, and L. Chen, “An adaptive fusion algorithm for spam detection,” IEEE Intell. Syst., vol. 29, no. 4, pp. 2–8, Jul./Aug. 2014.
[4]
Y. Kim, “Convolutional neural networks for sentence classification,” 2014. [Online]. Available: https://arxiv.org/abs/1408.5882
[5]
L. Yao, C. Mao, and Y. Luo, “Graph convolutional networks for text classification,” in Proc. Int. AAA Conf. Artif. Intell., 2019, pp. 7370–7377.
[6]
Y. Lin et al., “BertGCN: Transductive text classification by combining GCN and BERT,” 2021. [Online]. Available: https://arxiv.org/abs/2105.05727
[7]
J. Devlin, M. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” 2018. [Online]. Available: https://arxiv.org/abs/1810.04805
[8]
Y. Liu et al., “RoBERTa: A robustly optimized BERT pretraining approach,” 2019. [Online]. Available: https://arxiv.org/abs/1907.11692
[9]
C. Wan and B. Li, “Financial causal sentence recognition based on BERT-CNN text classification,” J. Supercomputing, vol. 78, no. 5, pp. 6503–6527, Apr. 2022.
[10]
D. Lu, “daminglu123 at SemEval-2022 task 2: Using BERT and LSTM to do text classification,” in Proc. Int. Workshop Semantic Eval., 2022, pp. 186–189.
[11]
L. X. Jiang, C. Q. Li, S. S. Wang, and L. G. Zhang, “Deep feature weighting for naive Bayes and its application to text classification,” Eng. Appl. Artif. Intell., vol. 52, pp. 26–39, Jun. 2016.
[12]
L. X. Jiang, S. S. Wang, C. Q. Li, and L. G. Zhang, “Structure extended multinomial naive Bayes,” Inf. Sci., vol. 329, pp. 346–356, Feb. 2016.
[13]
L. G. Zhang, L. X. Jiang, and C. Q. Li, “A new feature selection approach to naive Bayes text classifiers,” Int. J. Pattern Recognit. Artif. Intell., vol. 30, no. 2, Feb. 2016, Art. no. 1650003.
[14]
S. Lai, L. Xu, K. Liu, and J. Zhao, “Recurrent convolutional neural networks for text classification,” in Proc. Int. AAA Conf. Artif. Intell., 2015, pp. 2267–2273.
[15]
T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” 2016. [Online]. Available: https://arxiv.org/abs/1609.02907
[16]
Y. Dai et al., “Graph fusion network for text classification,” Knowl. Based Syst., vol. 236, Jan. 2022, Art. no. 107659.
[17]
Y. Sun et al., “ERNIE 2.0: A continual pre-training framework for language understanding,” 2019. [Online]. Available: https://arxiv.org/abs/1907.12412
[18]
L. Xiao, B. Cheng, and X. Huang, “Multi-label text classification based on semantic attention to labels,” J. Softw., vol. 31, no. 4, pp. 1079–1089, 2020.
[19]
S. Poria, E. Cambria, D. Hazarika, N. Majumder, A. Zadeh, and L. Morency, “Multi-level multiple attentions for contextual multimodal sentiment analysis,” in Proc. Int. Conf. Data Mining, 2017, pp. 1033–1038.
[20]
P. Liu, X. Qiu, and X. Huang, “Recurrent neural network for text classification with multi-task learning,” 2016. [Online]. Available: https://arxiv.org/abs/1605.05101
Recommendations
Improving Semi-Supervised Text Classification with Dual Meta-Learning
The goal of semi-supervised text classification (SSTC) is to train a model by exploring both a small number of labeled data and a large number of unlabeled data, such that the learned semi-supervised classifier performs better than the supervised ...
Combining Homogeneous Classifiers for Centroid-based Text Classification
ISCC '02: Proceedings of the Seventh International Symposium on Computers and Communications (ISCC'02)Centroid-based text classification is one of the most popular supervised approaches to classify texts into a set of pre-defined classes. Based on the vector-space model, the performance of this classification particularly depends on the way to weight ...
Vertical Ensemble Co-Training for Text Classification
Regular PapersHigh-quality, labeled data is essential for successfully applying machine learning methods to real-world text classification problems. However, in many cases, the amount of labeled data is very small compared to that of the unlabeled, and labeling ...
Comments
Information & Contributors
Information
Published In
1541-1672 © 2023 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information.
Publisher
IEEE Educational Activities Department
United States
Publication History
Published: 01 July 2023
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 25 Oct 2024
Other Metrics
Citations
View Options
View options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in