An Empirical Study of Multi-Task Learning on BERT for Biomedical Text Mining
This work addresses the challenge for biomedical researchers in selecting effective models for NLP tasks, though it is incremental as it builds on existing MTL and BERT methods.
The paper tackled the problem of improving performance on biomedical and clinical NLP tasks by applying multi-task learning to BERT, resulting in MTL fine-tuned models outperforming state-of-the-art transformer models by 2.0% in biomedical and 1.3% in clinical domains.
Multi-task learning (MTL) has achieved remarkable success in natural language processing applications. In this work, we study a multi-task learning model with multiple decoders on varieties of biomedical and clinical natural language processing tasks such as text similarity, relation extraction, named entity recognition, and text inference. Our empirical results demonstrate that the MTL fine-tuned models outperform state-of-the-art transformer models (e.g., BERT and its variants) by 2.0% and 1.3% in biomedical and clinical domains, respectively. Pairwise MTL further demonstrates more details about which tasks can improve or decrease others. This is particularly helpful in the context that researchers are in the hassle of choosing a suitable model for new problems. The code and models are publicly available at https://github.com/ncbi-nlp/bluebert