A Deep Reinforced Sequence-to-Set Model for Multi-Label Text Classification

TL;DR

This paper introduces a deep reinforcement learning-based sequence-to-set model for multi-label text classification, effectively capturing label correlations without requiring predefined label order, leading to significant performance improvements.

Contribution

The paper proposes a novel sequence-to-set framework using deep reinforcement learning to better model label correlations without relying on label order in MLTC.

Findings

Outperforms baseline models significantly

Effectively captures label correlations

Reduces dependence on label order

Abstract

Multi-label text classification (MLTC) aims to assign multiple labels to each sample in the dataset. The labels usually have internal correlations. However, traditional methods tend to ignore the correlations between labels. In order to capture the correlations between labels, the sequence-to-sequence (Seq2Seq) model views the MLTC task as a sequence generation problem, which achieves excellent performance on this task. However, the Seq2Seq model is not suitable for the MLTC task in essence. The reason is that it requires humans to predefine the order of the output labels, while some of the output labels in the MLTC task are essentially an unordered set rather than an ordered sequence. This conflicts with the strict requirement of the Seq2Seq model for the label order. In this paper, we propose a novel sequence-to-set framework utilizing deep reinforcement learning, which not only captures the correlations between labels, but also reduces the dependence on the label order. Extensive experimental results show that our proposed method outperforms the competitive baselines by a large margin.