Skip to main content

Table 1 Performance of various deep neural network methods on ADR extraction task

From: Semi-Supervised Recurrent Neural Network for Adverse Drug Reaction mention extraction

Method

F1-Score

Precision

Recall

Baseline [9]

0.729 ±0.027

0.695 ±0.109

0.776 ±0.121

Baseline (with adam optimizer)

0.737 ±0.308

0.707 ±0.096

0.774 ±0.08

Semi-Supervised ADR extraction

0.751 ±0.036*

0.731 ±0.035*

0.774 ±0.073

  1. ⋆Indicate statistical significant (p≤0.05) using paired t-tests compared to the baseline
  2. Highlighted portions reflect the best results across the respective column
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us