Skip to main content

Table 5 Prediction performance of our system without syntactic re-ranking among the semantically most similar top (k = 1, 5, 10, 20, 25, 50) concepts

From: Linking entities through an ontology using word embeddings and syntactic re-ranking

k

1

5

10

15

20

25

50

Train

0.614

0.656

0.672

0.711

0.726

0.738

0.831

Dev

0.655

0.683

0.725

0.753

0.789

0.804

0.894

  1. Precision values for the training and development data sets are reported when the reference concept is among the top k
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us