A Discriminative Deep Neural Network for Text Classification
Jiaxun Gao, Xiang Li, Zexuan Huang · 2021 International Conference on Computer Information Science and Artificial Intelligence (CISAI) · 2021
Text classification plays an important role in natural language processing. It has been widely applied to sentiment analysis, stance detection and fake news detection. Although previous work on text classification has made great progress in recent years, these methods do not consider discriminative. And the ignoration degrades the performance of text classification. Hence, this paper proposes a novel CNN-based method, which incorporates the power of discriminative by adding an extra regularization term. We conduct experiments on three datasets, and the results demonstrate that our model is superior to other popular text classification methods.