Table 4 The performance (weighted macro-average metric) of CNN based multi-class classification model on validation set
From: An application of convolutional neural networks with salient features for relation classification
Group No | Accuracy | Precision | Recall | F1 score |
|---|---|---|---|---|
| Â | Max/Ave/Min | Max/Ave/Min | Max/Ave/Min | Max/Ave/Min |
Group 1 | 77.74/68.69/60.74 | 88.54/49.78/26.35 | 11.11/10.5/10.25 | 47.70/36.3/21.44 |
Group 2 | 76.67/63.68/44.24 | 76.67/55.67/20.23 | 11.11/10.22/10.00 | 86.80/67.19/25.18 |
Group 3 | 76.91/63.77/44.47 | 76.91/64.50/48.15 | 11.11/10.26/10.00 | 86.95/69.33/21.82 |
Group 4 | 76.91/63.77/44.24 | 76.91/63.77/44.24 | 11.11/10.22/10.00 | 86.95/77.26/61.34 |
Group 5 | 76.91/63.77/44.24 | 76.91/63.77/44.24 | 11.11/10.22/10.00 | 86.95/77.26/61.34 |