LiGCN: Label-interpretable Graph Convolutional Networks for Multi-label Text Classification
This addresses multi-label text classification for NLP applications, offering improved interpretability, but it is incremental as it builds on existing graph-based methods.
The paper tackles multi-label text classification by proposing a label-interpretable graph convolutional network that models tokens and labels in a heterogeneous graph, achieving gains of 0.14 and 0.07 in F1 scores for small and large label sets, respectively.
Multi-label text classification (MLTC) is an attractive and challenging task in natural language processing (NLP). Compared with single-label text classification, MLTC has a wider range of applications in practice. In this paper, we propose a label-interpretable graph convolutional network model to solve the MLTC problem by modeling tokens and labels as nodes in a heterogeneous graph. In this way, we are able to take into account multiple relationships including token-level relationships. Besides, the model allows better interpretability for predicted labels as the token-label edges are exposed. We evaluate our method on four real-world datasets and it achieves competitive scores against selected baseline methods. Specifically, this model achieves a gain of 0.14 on the F1 score in the small label set MLTC, and 0.07 in the large label set scenario.