LiGCN: Label-interpretable Graph Convolutional Networks for Multi-label Text Classification

TL;DR

LiGCN introduces a label-interpretable graph convolutional network for multi-label text classification, modeling tokens and labels as nodes to improve interpretability and achieve competitive results on real datasets.

Contribution

The paper presents a novel GCN model that enhances interpretability in MLTC by explicitly modeling token-label relationships in a heterogeneous graph.

Findings

Achieves a 0.14 F1 score gain in small label set MLTC

Achieves a 0.07 F1 score gain in large label set MLTC

Demonstrates competitive performance on four real-world datasets

Abstract

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.