Integrating information by Kullback–Leibler constraint for text classification

Shu Yin, Peican Zhu, Xinyu Wu, Jiajin Huang, Xianghua Li, Zhen Wang, Chao Gao

科研成果: 期刊稿件文章同行评审

4 引用 (Scopus)

摘要

Text classification is an important assignment for various text-related downstream assignments, such as fake news detection, sentiment analysis, and question answering. In recent years, the graph-based method achieves excellent results in text classification tasks. Instead of regarding a text as a sequence structure, this method regards it as a co-occurrence set of words. The task of text classification is then accomplished by aggregating the data from nearby nodes using the graph neural network. However, existing corpus-level graph models are difficult to incorporate the local semantic information and classify new coming texts. To address these issues, we propose a Global–Local Text Classification (GLTC) model, based on the KL constraints to realize inductive learning for text classification. Firstly, a global structural feature extractor and a local semantic feature extractor are designed to capture the structural and semantic information of text comprehensively. Then, the KL divergence is introduced as a regularization term in the loss calculation process, which ensures that the global structural feature extractor can constrain the learning of the local semantic feature extractor to achieve inductive learning. The comprehensive experiments on benchmark datasets present that GLTC outperforms baseline methods in terms of accuracy.

源语言英语
页(从-至)17521-17535
页数15
期刊Neural Computing and Applications
35
24
DOI
出版状态已出版 - 8月 2023

指纹

探究 'Integrating information by Kullback–Leibler constraint for text classification' 的科研主题。它们共同构成独一无二的指纹。

引用此