Skip to main content

Table 6 Results of relation detection algorithm for Titles and PMAs

From: Digital surveillance in Latin American diseases outbreaks: information extraction from a novel Spanish corpus

Relation

Titles

PMAs

P

R

F1

P

R

F1

DsOccIn

0.93

1.00

0.97

0.89

0.89

0.89

DtDs

   

0.92

0.87

0.90

NegDs

0.00

0.00

0.00

0.51

0.95

0.67

NegNoC

   

0.42

1.00

0.60

NegOr

1.00

1.00

1.00

0.75

1.00

0.86

NegTf

   

0.57

1.00

0.72

NoCDs

0.88

1.00

0.93

0.82

0.91

0.86

NoCHst

   

0.48

0.97

0.64

NoCLoc

0.67

1.00

0.80

0.33

0.91

0.48

OccTo

0.89

1.00

0.94

0.83

0.88

0.86

OrDs

0.79

1.00

0.89

0.87

0.86

0.86

OrOccIn

0.33

1.00

0.50

0.30

0.76

0.43

PtDs

   

0.56

0.92

0.70

PtNoC

   

0.67

0.93

0.78

TfDs

0.65

1.00

0.79

0.62

0.82

0.71

TfOccIn

0.44

1.00

0.61

0.31

1.00

0.47

TfOr

0.50

1.00

0.67

0.76

0.93

0.84

UcDs

0.45

1.00

0.62

0.29

0.96

0.45

UcNoC

   

0.57

0.98

0.72

UcOr

1.00

1.00

1.00

0.76

0.96

0.85

UcTf

0.50

1.00

0.67

0.75

0.90

0.82

UcNoCDs

   

0.29

0.43

0.35

UcOrDs

0.33

0.33

0.33

0.27

0.31

0.29

UcTfDs

0.00

0.00

0.00

0.00

0.00

0.00

Micro-avg

0.86

1.00

0.92

0.62

0.90

0.73

  1. Binary and ternary relations’ Precision (P), recall (R) and F1-score are shown. Also micro-averaged metrics are shown