Skip to main content

Table 3 Performance of CollaboNet and the Multi-Task Model by Wang et al. [25]

From: CollaboNet: collaboration of deep neural networks for biomedical named entity recognition

Model Wang et al. (2018) MTM CollaboNet
Dataset Precision Recall F1 Score Precision Recall F1 Score
NCBI-disease 85.86 86.42 86.14 85.48 87.27 86.36(±0.54)
JNLPBA 70.91 76.34 73.52 74.43 83.22 78.58
BC5CDR-chem *93.09 *89.56 *91.29 94.26 92.38 93.31
BC5CDR-disease *83.73 *82.93 *83.33 85.61 82.61 84.08
BC4CHEMD 91.30 87.53 89.37 90.78 87.01 88.85
BC2GM 82.10 79.42 80.74 80.49 78.99 79.73
Macro Average 84.50 83.70 84.07 85.18 85.25 85.15
  1. Scores in the asterisked (*) cells are obtained in the experiments that we conducted; these scores are not reported in the original papers. The best scores from these experiments are in bold