文献类型：会议论文

英文题名：Fine-tuning BERT for Joint Entity and Relation Extraction in Chinese Medical Text

作者：Xue, Kui[1];Zhou, Yangming[1];Ma, Zhiyuan[1];Ruan, Tong[1];Zhang, Huanhuan[1];He, Ping[2]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China;[2]Shanghai Hosp Dev Ctr, Shanghai 200041, Peoples R China

会议论文集：IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

会议日期：NOV 18-21, 2019

会议地点：San Diego, CA

语种：英文

外文关键词：Named entity recognition; Relation classification; Joint model; BERT language model; Electronic health records

摘要：Entity and relation extraction is the necessary step in structuring medical text. However, the feature extraction ability of the bidirectional long short term memory network in the existing model does not achieve the best effect. At the same time, the language model has achieved excellent results in more and more natural language processing tasks. In this paper, we present a focused attention model for the joint entity and relation extraction task. Our model integrates well-known BERT language model into joint learning through dynamic range attention mechanism, thus improving the feature representation ability of shared parameter layer. Experimental results on coronary angiography texts collected from Shuguang Hospital show that the F-1-scores of named entity recognition and relation classification tasks reach 96.89% and 88.51%, which outperform state-of-the-art methods by 1.65% and 1.22%, respectively.