Skip to main content

Table 6 Results on test data.

From: Sieve-based relation extraction of gene regulatory networks from biological literature

Setting

S

D

I

M

SER

wo. (vii) & wo. cleaning

4

51

8

33

0.72

wo. (vii) & cleaning

4

51

5

33

0.68

(vii) & wo. cleaning

5

47

15

36

0.76

(vii) & cleaning

5

47

12

36

0.73

  1. The table shows results on the test set using new feature functions and the additional sieve (vii) with or without data cleaning. The abbreviations represent the number of substitutions (S), deletions (D), insertions (I) and matches (M). Best results per metric are highlighted in bold.
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us