Rafael Antonio Ribeiro Gomes
Rafael Antonio Ribeiro Gomes
If I understand right, you are trying to extend your dataset with data that is not labeled. In this case, your Precision and Recall will only increase for "O" (BILOU)....
As far as I know, it will depend on the size of your datasets. Also, check the memory usage (maybe you are out of memory and the system starts to...
Increasing dropout values may help you.
No, as far as I know, changing the learning rate will not prevent the overfitting.
Why are we setting to 0? Seems we had values != 0 previously.