A Deep Reinforced Sequence-to-Set Model for Multi-Label Text Classification
This work solves the issue of label order dependence in multi-label classification for NLP applications, representing an incremental improvement over existing methods.
The paper tackled the problem of multi-label text classification by addressing the mismatch between unordered label sets and sequence generation models, proposing a sequence-to-set framework with deep reinforcement learning that outperformed baselines by a large margin.
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.