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