Skip to main content
. 2018 Jun 13;19(Suppl 8):209. doi: 10.1186/s12859-018-2195-1

Table 3.

Results obtained for max-pooling CNN on the test dataset with negative filtering

Classes P R F1
Advise 80.36% 61.09% 69.41%
Effect 62.06% 64.15% 63.09%
Int 62.32% 44.79% 52.12%
Mechanism 67.24% 66.11% 66.67%
Overall 67.19% 62.14% 64.56%