Abstract

Recently, the Capsule Network is an emerging neural network structure that is characterized by the ability to maintain high classification accuracy. By analyzing the difference between Capsule Network and traditional convolutional neural network, it is found that the model compression method applied to the traditional neural network cannot be directly used in the Capsule Network. To address the problem, an IPC-CapsNet compression algorithm is proposed based on the structural characteristics of the Capsule Networks. The algorithm can reduce the computational complexity and compress the scale of model computation on the basis of retaining the accuracy of model classification. Considering the deficiency of Capsule Network processing serialized text data separately, we combined with IPC-CapsNet and then come up with a sentiment classification algorithm SPT-CapsNet. It has conducted a sentiment analysis experiment of MicroBlog dataset. Compared to other methods, our SPT-CapsNet obtained the best performance among the metrics. The SPT-CapsNet improves the running speed and maintains the balance between classification accuracy and computational efficiency.

中文翻译：

---

基于SPT-CapsNet的情感分类算法

摘要

最近，胶囊网络是一种新兴的神经网络结构，其特征在于能够保持较高的分类精度。通过分析胶囊网络与传统卷积神经网络的区别，发现应用于传统神经网络的模型压缩方法不能直接用于胶囊网络。为了解决该问题，基于胶囊网络的结构特点，提出了一种IPC-CapsNet压缩算法。该算法可以在保持模型分类精度的基础上，降低计算复杂度，压缩模型计算规模。考虑到Capsule Network单独处理序列化文本数据的缺陷，我们结合了IPC-CapsNet，然后提出了情感分类算法SPT-CapsNet。它已经进行了MicroBlog数据集的情感分析实验。与其他方法相比，我们的SPT-CapsNet在各项指标中获得了最佳性能。SPT-CapsNet提高了运行速度，并保持了分类精度和计算效率之间的平衡。