Multi-Label Text Classification using Attention-based Graph Neural Network

Abstract

In Multi-Label Text Classification (MLTC), one sample can belong to more than one class. It is observed that most MLTC tasks, there are dependencies or correlations among labels. Existing methods tend to ignore the relationship among labels. In this paper, a graph attention network-based model is proposed to capture the attentive dependency structure among the labels. The graph attention network uses a feature matrix and a correlation matrix to capture and explore the crucial dependencies between the labels and generate classifiers for the task. The generated classifiers are applied to sentence feature vectors obtained from the text feature extraction network (BiLSTM) to enable end-to-end training. Attention allows the system to assign different weights to neighbor nodes per label, thus allowing it to learn the dependencies among labels implicitly. The results of the proposed model are validated on five real-world MLTC datasets. The proposed model achieves similar or better performance compared to the previous state-of-the-art models.

References in corpus (4)

• Distributed Representations of Words and Phrases and their Compositionality
• Effective Use of Word Order for Text Categorization with Convolutional Neural Networks
• A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applications
• Hierarchical Text Classification with Reinforced Label Assignment

Cited by in corpus (6)

• A Survey on Text Classification: From Shallow to Deep Learning
• Well-calibrated Confidence Measures for Multi-label Text Classification with a Large Number of Labels
• Large Scale Legal Text Classification Using Transformer Models
• KeNet:Knowledge-enhanced Doc-Label Attention Network for Multi-label text classification
• Balancing Methods for Multi-label Text Classification with Long-Tailed Class Distribution
• Label prompt for multi-label text classification