Add parameter for changing loss for NONE

[isabelleaugenstein]

...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