Skip to main content

Table 10 Average standard deviation of ratings per subset by word-frequency.

From: Bio-SimVerb and Bio-SimLex: wide-coverage evaluation sets of word similarity in biomedicine

Frequency subset

Bio-SimVerb

Bio-SimLex

Low

0.9848

1.5621

Medium

0.8059

0.6784

High

1.2352

1.0237

Average

1.009

1.088

  1. We use: low, medium and high to label subsets for brevity. Range values of corresponding subsets can be found in Figs. 1 and 2
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us