Skip to main content
. 2018 Feb 5;19:33. doi: 10.1186/s12859-018-2039-z

Table 6.

Pearson’s correlation between word-similarity/Bio-SimVerb and Bio-SimLex scores and the NER tasks evaluated on biomedical representation models trained with different approaches. None of the scores are statistically significant

BC4CHEMD BC2GM AnatEM JNLPBA
UMN-rel -0.15 -0.14 -0.08 -0.07
UMN-sim -0.38 -0.34 -0.34 -0.3
MayoSRS 0.08 0.04 0.18 0.12
Bio-SimVerb 0.2 0.18 0.29 0.24
Bio-SimLex 0.53 0.6 0.46 0.48

Bold: best scores