Skip to main content

Table 5 Error rates of the combined classifier

From: Using contextual and lexical features to restructure and validate the classification of biomedical concepts

 

The entire test set

(N = 223)

≥ 1 syntactic dependencies

(N = 192)

≥ 10 syntactic dependencies

(N = 91)

Type of features

Error rate

MRR

Error rate

MRR

Error rate

MRR

Syntactic dependencies

+

Strings without annotations

0.191

w = 0

0.881

0.167

w = 0.2

0.900

0.110

w = 0.3

0.935

Syntactic dependencies

+

Strings with annotations

0.143

w = 0

0.907

0.143

w = 0.3

0.912

0.055

w = 0.3

0.969

  1. * Note that in the first column we set w = 0 because the distributional approach is not applicable.