Label-Dividing Gated Graph Neural Network for Hierarchical Text Classification
Authors:
- 18 July 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 01-08
Abstract
Multi-label hierarchical text classification (MLHTC) is an essential yet challenging task of natural language processing (NLP). Existing methods lack attention to predicting sibling labels. In addition, methods based on graph convolutional networks (GCN) meet the problem of over-smoothing, which further deepens the difficulty of distinguishing sibling labels. In this paper, we propose a label-dividing gated graph neural network (LD-GGNN), which can better distinguish sibling labels and achieve adaptive interaction between text and labels. We optimize gated graph neural network (GGNN) to accurately capture structural features of label hierarchy and deeply explore label dependence. Stronger nonlinear characteristics of GGNN are used to solve the problem of over-smoothing. Furthermore, we propose a dynamic label dividing mechanism (DLDM), which can guide the model to distinguish sibling labels by introducing a dividing bias. Compared with previous works, LD-GGNN achieves significant and consistent improvements on both Micro-F1 and Macro-F1 score on multiple datasets.Keywords
This publication has 17 references indexed in Scilit:
- A Residual Dynamic Graph Convolutional Network for Multi-label Text Classification2021
- Label-Specific Dual Graph Neural Network for Multi-Label Text Classification2021
- Hyperbolic Capsule Networks for Multi-Label Classification2020
- Hierarchy-Aware Global Model for Hierarchical Text Classification2020
- HDLTex: Hierarchical Deep Learning for Text Classification2017
- Deep Learning for Extreme Multi-label Text Classification2017
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- Hierarchical multi-label classification using local neural networksJournal of Computer and System Sciences, 2014
- Recursive regularization for large-scale classification with hierarchical and graphical dependencies2013
- Hierarchical classification of Web content2000