Add parameter for changing loss for NONE
isabelleaugenstein opened this issue · 0 comments
isabelleaugenstein commented
...because it doesn't contribute to Macro F1
Ignore the NONE training examples:
- multiplying the total loss by 1-target[0](so if the class is NONE the loss is 0)
- remove NONE examples from the training+dev corpus.
Or downweigh them:
loss = (1-(target[0] * (1 - alpha))) * loss
So for target class NONE and alpha 0.1 we would get:
loss = (1-(1_0.9))_loss = 0.1*loss