Local discriminative graph convolutional networks for text classification

Wang, Bolin; Sun, Yuan; Chu, Yonghe; Min, Changrong; Yang, Zhihao; Lin, Hongfei

doi:10.1007/s00530-023-01112-y

Cited by 3 publications

(1 citation statement)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 2014, Kim first introduced CNN into the field of natural language processing and proposed the TextCNN model [8] for text classification. Subsequently, a series of CNN-based text processing models [9][10][11][12] were proposed and applied to text classification tasks, proving the powerful semantic feature extraction ability of CNN. However, due to the limitations of the convolution kernel size, CNN has strong advantages in local feature extraction, but is difficult to extract long-distance dependency relationships within text.…”

Section: Introductionmentioning

confidence: 99%

A Multi-Layer Feature Fusion Model Based on Convolution and Attention Mechanisms for Text Classification

Yang

Zhang

Shen³

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Text classification is one of the fundamental tasks in natural language processing and is widely applied in various domains. CNN effectively utilizes local features, while the Attention mechanism performs well in capturing content-based global interactions. In this paper, we propose a multi-layer feature fusion text classification model called CAC, based on the Combination of CNN and Attention. The model adopts the idea of first extracting local features and then calculating global attention, while drawing inspiration from the interaction process between membranes in membrane computing to improve the performance of text classification. Specifically, the CAC model utilizes the local feature extraction capability of CNN to transform the original semantics into a multi-dimensional feature space. Then, global attention is computed in each respective feature space to capture global contextual information within the text. Finally, the locally extracted features and globally extracted features are fused for classification. Experimental results on various public datasets demonstrate that the CAC model, which combines CNN and Attention, outperforms models that solely rely on the Attention mechanism. In terms of accuracy and performance, the CAC model also exhibits significant improvements over other models based on CNN, RNN, and Attention.

show abstract