Open gabrer opened 5 years ago
Are the coefficients used while summing up the losses fixed? How did you choose them? In the original paper, they would be _alphat, where t is the particular task.
Thank you!
I think it is a hyper-parameter. I choose one with higher F1 score.
Ok, thank you! Still looking for any other approach.
Are the coefficients used while summing up the losses fixed? How did you choose them? In the original paper, they would be _alphat, where t is the particular task.
Thank you!