Skip to main content

Table 4 Comparison of the performance of cross-corpus evaluation for comparative methods using strict matching

From: Biomedical named entity recognition using deep neural networks with contextual information

Strict matching

train CDR → test NCBIa

train NCBI → test CDRb

Model

p

r

f

p

r

f

BiLSTM

57.32

37.92

45.64

55.19

30.79

39.52

BiLSTM-CRF

68.34

36.88

47.90

58.30

38.74

46.55

GRAM-CNN

59.74

42.81

49.88

58.48

33.21

42.36

BERT

68.92

53.13

60.00

54.17

61.44

57.57

CLSTM

word level

62.42

48.96

54.87

60.92

38.09

46.87

 

character level (3)c

68.12

44.06

53.51

62.74

32.66

42.96

 

character level (7)c

65.08

45.63

53.64

60.69

21.75

32.02

 

word+char levels (3, 3)d

66.77

43.75

52.86

54.00

44.08

48.54

 

word+char levels (5, 5)d

69.36

42.92

53.02

57.63

39.51

46.88

  1. aTest the disease entities in the NCBI corpus using the model trained on the CDR corpus
  2. bTest the disease entities in the CDR corpus using the model trained on the NCBI corpus
  3. cThe number in parentheses represents the window size at the character level.
  4. dThe numbers in parentheses represent the window sizes at the word and character level, respectively
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us