Table 3 Results obtained on Weibo and OneNote.

From: A Chinese named entity recognition model incorporating recurrent cell and information state recursion

Mould

Weibo

OneNote

P

R

F1

P

R

F1

BERT-LRCNN

57.14

66.67

59.92

76.40

72.60

74.45

Lattice-LSTM-CRF

53.04

62.25

58.79

76.35

71.56

73.88

BERT-BILSTM-CRF

69.65

64.62

67.33

81.99

81.65

81.82

BERT-PLTE-BIGRU-CRF

72.00

66.67

69.23

79.62

81.82

80.60

LGN

55.34

64.98

60.21

76.13

73.68

74.89

FGN

69.21

70.60

69.90

81.23

83.26

82.19

WC-GCN

55.38

62.98

59.31

75.05

72.29

73.64

MECT

61.91

62.51

63.30

77.57

76.27

76.92

Visphone

65.65

71.29

70.79

80.57

84.79

82.63

BERT-IRCSR-CRF

70.53

71.17

70.85

82.16

83.51

82.83

  1. Significant values are in bold.
Back to article page