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 |