Skip to main content

Table 2 Experimental results over five runs

From: A prefix and attention map discrimination fusion guided attention for biomedical named entity recognition

Datasets

Mean ± Std

Max

BC4CHEMD

92.55 ± (0.00)

92.55

BC2GM

85.35 ± (0.06)

85.45

BC5CDR-Disease

87.51 ± (0.02)

87.53

BC5CDR-Chem

94.10 ± (0.06)

94.16

NCBI-Disease

90.40 ± (0.08)

90.55

  1. “Max” denotes the maximum F1-score, “Mean” denotes the average F1-score, and “Std” denotes the standard deviation. The best scores are shown in bold
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us