TCNNn Text Classification Model based on nAdam Optimizer
Zhiyi Xie, Yanli Wang, Shibao Sun · Proceedings of the 7th International Conference on Cyber Security and Information Engineering · 2022
With the rapid development of mobile Internet, complicated information appears in people's life in various forms. As one of the main carriers of information, text plays the role of information transmission bridge in life, but in the face of mixed data, relying on computers to efficiently process text has become an excellent and necessary choice. This paper proposes a TCNNn (Transformer+CNN+nAdam) model based on the improved Adam optimizer and the integration of Transformer mechanism. By learning and calculating the contribution size of input data through the attention mechanism, the autocorrelation of each word in the text is established. A classification experiment is carried out on the news text data set. In addition, in order to further verify the effectiveness of the model, ablation experiment was also carried out at the end of this paper. The results of both the comparative experiment and ablation experiment confirmed that the model did improve the text classification evaluation index compared with the baseline model, which verified the effectiveness of the model.