Chinese clinical named entity recognition via multi-head self-attention based BiLSTM-CRF

作者：

Highlights：

• A Multi-head Self-attention-based BiLSTM-CRF model (MUSA-BiLSTM-CRF) for Chinese clinical named entity recognition

• An improved character-level feature representation method combining character embedding and character-label embedding

• Performance evaluation of models on the CCKS 2017 Task 2 benchmark dataset and the CCKS 2018 Task 1 benchmark dataset.

摘要

•A Multi-head Self-attention-based BiLSTM-CRF model (MUSA-BiLSTM-CRF) for Chinese clinical named entity recognition•An improved character-level feature representation method combining character embedding and character-label embedding•Performance evaluation of models on the CCKS 2017 Task 2 benchmark dataset and the CCKS 2018 Task 1 benchmark dataset.

论文关键词：Chinese clinical named entity recognition,Self-attention mechanism,Multi-head attention,Conditional random field,Bidirection long-short term memory

论文评审过程：Received 10 July 2020, Revised 26 May 2021, Accepted 15 March 2022, Available online 18 March 2022, Version of Record 24 March 2022.

论文官网地址：https://doi.org/10.1016/j.artmed.2022.102282