TY - GEN
T1 - Named Entity Recognition Using BERT BiLSTM CRF for Chinese Electronic Health Records
AU - Dai, Zhenjin
AU - Wang, Xutao
AU - Ni, Pin
AU - Li, Yuming
AU - Li, Gangmin
AU - Bai, Xuming
N1 - Funding Information:
This work is partially supported by the AI University Research Centre (AI-URC) through XJTLU Key Programme Special Fund (KSF-P-02) and KSF-A-17. And it is also partially supported by Suzhou Science and Technology Programme Key Industrial Technology Innovation programme with project code SYG201840. We appreciate their support and guidance.
Funding Information:
This work is partially supported by the AI University Research Centre (AI-URC) through XJTLU Key Programme Special Fund (KSF-P-02) and KSF-A-17. And it is also partially supported by Suzhou Science and Technology Programme Key Industrial Technology Innovation programme with project code SYG201840.
Publisher Copyright:
© 2019 IEEE.
PY - 2019/10
Y1 - 2019/10
N2 - As the generation and accumulation of massive electronic health records (EHR), how to effectively extract the valuable medical information from EHR has been a popular research topic. During the medical information extraction, named entity recognition (NER) is an essential natural language processing (NLP) task. This paper presents our efforts using neural network approaches for this task. Based on the Chinese EHR offered by CCKS 2019 and the Second Affiliated Hospital of Soochow University (SAHSU), several neural models for NER, including BiLSTM, have been compared, along with two pre-trained language models, word2vec and BERT. We have found that the BERT-BiLSTM-CRF model can achieve approximately 75% F1 score, which outperformed all other models during the tests.
AB - As the generation and accumulation of massive electronic health records (EHR), how to effectively extract the valuable medical information from EHR has been a popular research topic. During the medical information extraction, named entity recognition (NER) is an essential natural language processing (NLP) task. This paper presents our efforts using neural network approaches for this task. Based on the Chinese EHR offered by CCKS 2019 and the Second Affiliated Hospital of Soochow University (SAHSU), several neural models for NER, including BiLSTM, have been compared, along with two pre-trained language models, word2vec and BERT. We have found that the BERT-BiLSTM-CRF model can achieve approximately 75% F1 score, which outperformed all other models during the tests.
KW - BiLSTM-CRF
KW - Electronic Health Records
KW - Named Entity Recognition
UR - http://www.scopus.com/inward/record.url?scp=85079164262&partnerID=8YFLogxK
U2 - 10.1109/CISP-BMEI48845.2019.8965823
DO - 10.1109/CISP-BMEI48845.2019.8965823
M3 - Conference Proceeding
AN - SCOPUS:85079164262
T3 - Proceedings - 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019
BT - Proceedings - 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019
A2 - Li, Qingli
A2 - Wang, Lipo
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics, CISP-BMEI 2019
Y2 - 19 October 2019 through 21 October 2019
ER -