[nlp] JointBert FocalLoss

import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.autograd import Variable
 
class FocalLoss(nn.Module):
    r"""
        This criterion is a implemenation of Focal Loss, which is proposed in 
        Focal Loss for Dense Object Detection.
            Loss(x, class) = - \alpha (1-softmax(x)[class])^gamma \log(softmax(x)[class])
        The losses are averaged across observations for each minibatch.
        Args:
            alpha(1D Tensor, Variable) : the scalar factor for this criterion
            gamma(float, double) : gamma > 0; reduces the relative loss for well-classified examples (p > .5), 
                                   putting more focus on hard, misclassified examples
            size_average(bool): By default, the losses are averaged over observations for each minibatch.
                                However, if the field size_average is set to False, the losses are