BMC Medical Informatics and Decision Making

Table 4 Performance after adding POS information

From: A deep learning model incorporating part of speech and self-matching attention for named entity recognition of Chinese electronic medical records

	LSTM-CRF		SM-LSTM-CRF
	Character	Character + POS	Character	Character + POS
P	0.6568	0.7606	0.6858	0.7819
R	0.6904	0.7487	0.6991	0.7713
F	0.6732	0.7546	0.6991	0.7765

Back to article page

ISSN: 1472-6947

Contact us

General enquiries: journalsubmissions@springernature.com