Table 6.
Results obtained for the combination of max-pooling and attentive pooling CNN on the test dataset corpus with negative filtering
Classes | P | R | F1 |
---|---|---|---|
Advise | 79.23% | 65.61% | 71.78% |
Effect | 65.28% | 61.62% | 63.40% |
Int | 80.49% | 34.38% | 48.18% |
Mechanism | 69.23% | 60.40% | 64.52% |
Overall | 70.40% | 59.47% | 64.47% |