Skip to main content

Table 10 Token level errors in percentages by type (correctly and incorrectly tagged) and possible error sources

From: Recent advances in Swedish and Spanish medical entity recognition in clinical texts using deep neural approaches

 

Swedish

Spanish

 

OOEV

AAV

OOTV

OOEV

AAV

OOTV

Correct

8.04

9.51

38.38

4.09

9.13

39.37

Incorrect

11.30

10.43

66.38

4.56

13.69

58.94

Both

6.90

33.50

40.91

2.34

40.11

33.45

Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us