4.6 Article

Siamese capsule networks with global and local features for text classification

期刊

NEUROCOMPUTING
卷 390, 期 -, 页码 88-98

出版社

ELSEVIER
DOI: 10.1016/j.neucom.2020.01.064

关键词

Text classification; Capsule networks; Siamese networks; Neural networks; Global and local features

资金

  1. National Natural Science Foundation of China [41201404]
  2. Fundamental Research Funds for the Central Universities of China [2042015gf0009]

向作者/读者索取更多资源

Text classification is a popular research topic in the field of natural language processing and provides wide applications. The existing text classification methods based on deep neural networks can completely extract the local features of text. The text classification models constructed based on these methods yield good experimental results. However, these methods generally ignore the global semantic information of different categories of text and global spatial distance between categories. To some extent, this adversely affects the accuracy of classification. In this study, to address this problem, Siamese capsule networks with global and local features were proposed. A Siamese network was used to glean information about the global semantic differences between categories, which could more accurately represent the semantic distance between different categories. A global memory mechanism was established to store global semantic features, which were then incorporated into the text classification model. Capsule vectors were used to obtain the spatial position relationships of local features, thereby improving the representation capabilities of the features. The experimental results showed that the proposed model achieved better results and performed significantly better on six different public datasets, as compared with ten baseline algorithms. (C) 2020 Elsevier B.V. All rights reserved.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据