Skip to main content

Table 4 Results of the proposed method with/without re-ranking on the adverse drug reaction normalization task

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

 

Baseline

Before Re-ranking

After Re-ranking

Training set

Macro-average Precision

0.999

0.737

0.742

Macro-average Recall

0.522

0.732

0.736

Macro-average F-score

0.686

0.735

0.739

Micro-average Precision

0.999

0.728

0.730

Micro-average Recall

0.513

0.723

0.725

Micro-average F-score

0.665

0.726

0.728

Test set

Macro-average Precision

0.999

0.683

0.687

Macro-average Recall

0.494

0.677

0.681

Macro-average F-score

0.661

0.675

0.684

Micro-average Precision

0.999

0.682

0.686

Micro-average Recall

0.489

0.675

0.680

Micro-average F-score

0.657

0.678

0.684

  1. Precision, recall and f-score values for the training and test sets are reported
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us