Skip to main content

Table 7 The effect of using the BANNER entity tagger compared to gold-standard entities on the performance (precision, recall and F-score) of our simple baseline algorithm, Baseline(K).

From: A realistic assessment of methods for extracting gene/protein interactions from free text

 

A

B

H

I

(L)

Precision:

     

With gold-standard entities

22.8

24

54

44.8

53.9

With BANNER

18.4

23.5

32

20

43.8

Δ precision

4.4

0.5

22

24.8

10.1

Recall:

     

With gold-standard entities

51.5

52.2

66.9

56.4

72

With BANNER

42.1

33.5

49.7

27.5

51.2

Δ recall

9.4

18.7

17.2

28.9

20.8

F-score:

     

With gold-standard entities

31.6

32.9

59.7

49.9

61.6

With BANNER

25.6

27.6

38.9

23.1

47.2

Δ F-score

6

5.3

20.8

26.8

14.4

  1. Corpus abbreviations are as follows: A = AIMed; B = BioInfer; H = HPRD50; I = IEPA; L = LLL.