Multi-Label Text Classification using Attention-based Graph Neural Network
This addresses the challenge of label correlations in multi-label text classification for applications like document tagging, but it is incremental as it builds on existing graph and attention methods.
The paper tackled the problem of multi-label text classification by proposing an attention-based graph neural network to capture label dependencies, achieving similar or better performance compared to previous state-of-the-art models on five real-world datasets.
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.