Biomedical Named Entity Recognition Through Deep Reinforcement Learning

作者：Zhehuan Zhao, Yuying Zou, Menghan Wang, Bo Xu, Zhihao Yang, Hongfei Lin · 年份：2023 · DOI：10.1109/bibm58861.2023.10386014 · 被引用次数：2 · 研究领域：Topic Modeling、Biomedical Text Mining and Ontologies、Natural Language Processing Techniques

Biomedical Named Entity Recognition (BioNER) is a crucial task in extracting entities from biomedical literature. It plays a key role as the initial step in various biomedical information extraction tasks. Pre-training models have gained popularity in BioNER. However, these models require a large number of parameters, which poses a barrier for many researchers due to the hardware resource requirements. To address this challenge, we propose REIN-NER, a novel reinforcement learning-based approach for BioNER. REIN-NER employs a two-stage training mechanism: Firstly, the basic named recognition model (BaseNER) is pre-trained to capture the mapping knowledge from input words to the corresponding labels. Secondly, after initializing the agent model (AgentNER) with the BaseNER, the reinforcement training is carried out to further obtain the dependency knowledge between the output labels. Both BaseNER and AgentNER are built with lightweight Bi-LSTM networks, which significantly reduce parameter sizes compared to pre-training models. Remarkably, REIN-NER achieves superior performance with F-scores of 84.04% and 93.34% on the CDR-disease and CDR-chemical corpora, respectively, outperforming BERT-based models. Our work presents a pioneering exploration of reinforcement learning in biomedical named entity recognition and demonstrates its effectiveness through state-of-the-art results.