Label-Wise Document Pre-Training for Multi-Label Text Classification
This work addresses multi-label text classification for researchers and practitioners, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the challenge of exploiting label differences and correlations in multi-label text classification by developing a Label-Wise Pre-Training method, which achieves significant advantages over previous state-of-the-art models and discovers reasonable label relationships.
A major challenge of multi-label text classification (MLTC) is to stimulatingly exploit possible label differences and label correlations. In this paper, we tackle this challenge by developing Label-Wise Pre-Training (LW-PT) method to get a document representation with label-aware information. The basic idea is that, a multi-label document can be represented as a combination of multiple label-wise representations, and that, correlated labels always cooccur in the same or similar documents. LW-PT implements this idea by constructing label-wise document classification tasks and trains label-wise document encoders. Finally, the pre-trained label-wise encoder is fine-tuned with the downstream MLTC task. Extensive experimental results validate that the proposed method has significant advantages over the previous state-of-the-art models and is able to discover reasonable label relationship. The code is released to facilitate other researchers.