Skip to main content

Table 3 The effectiveness of the application of full-sentence and SDP features according to the mean F1 scores of 30 different random seeds

From: Relation extraction between bacteria and biotopes from biomedical texts with attention mechanisms and domain-specific contextual representations

Model

F1 score

Fulls

SDPs

Mean

SD

Min

Max

-

CNN

43.79

3.39

37.02

51.82

BLSTM

-

41.22

14.49

12.82

49.93

BLSTM

CNN

45.96

2.87

42.09

52.19

  1. All of the highest scores are highlighted in bold except for the SD
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us