Skip to main content

Table 3 Experimental results – AIMED data set

From: Combining active learning and semi-supervised learning techniques to extract protein interaction sentences

Algorithms

Measures

 

Precision

Recall

F-score

SVM

55.15%

42.47%

48.14%

RS-SVM

56.98%

41.71%

48.92%

C-SVM

64.53%

40.42%

50.67%

BT-SVM

65.23%

42.51%

53.64%

BTDA-SVM

74.34%

50.75%

61.91%

Yakushiji et al. [15]

33.70%

33.10%

33.40%

Mitsumori et al. [16]

54.20%

42.60%

47.70%