Skip to main content

Table 5 Results for Spanish

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

Source

Feature

Algorithm

Precision

Recall

F1-score

EHR

W

Glove

71.97

60.33

65.64

  

word2vec

72.48

69.34

70.87

  

FastText

73.82

69.84

71.77

 

L

Glove

74.22

67.21

70.54

  

word2vec

80.18

70.90

75.25

  

FastText

76.71

66.86

71.44

GenMed

W

Glove

70.42

64.73

67.46

  

word2vec

75.15

68.91

71.90

  

FastText

75.02

66.08

70.26

 

L

Glove

73.53

65.86

69.49

  

word2vec

75.15

63.31

68.72

  

FastText

72.18

66.64

69.30

Gen

W

Glove

71.54

65.65

68.47

  

word2vec

70.63

61.60

65.81

  

FastText

73.97

62.74

67.90

 

L

Glove

73.00

64.66

68.57

  

word2vec

74.11

63.38

68.32

  

FastText

75.87

63.38

69.06

EHR

W,L

word2vec

76.00

69.00

72.27

 

W+L

word2vec

76.52

65.93

70.83

 

W-L

word2vec

75.18

67.71

71.25

  1. Embeddings of base-units on top and, below, with the base-units combined