Fine-Tuning Pretrained Language Models With Label Attention for Biomedical Text Classification

The massive scale and growth of textual biomedical data have made its indexing and classification increasingly important. However, existing research on this topic mainly utilized convolutional and recurrent neural networks, which generally achieve inferior performance than the novel transformers. On the other hand, systems that apply transformers only focus on the target documents, overlooking the rich semantic information that label descriptions contain. To address this gap, we develop a transformer-based biomedical text classifier that considers label information. The system achieves this with a label attention module incorporated into the fine-tuning process of pretrained language models (PTMs). Our results on two public medical datasets show that the proposed fine-tuning scheme outperforms the vanilla PTMs and state-of-the-art models.