Dice Loss for Data-imbalanced NLP Tasks

Many NLP tasks such as tagging and machine reading comprehension (MRC) are faced with the severe data imbalance issue: negative examples significantly outnumber positive ones, and the huge number of easy-negative examples overwhelms training. The most commonly used cross entropy criteria is actually accuracy-oriented, which creates a discrepancy between training and test. At training time, each training instance contributes equally to the objective function, while at test time F1 score concerns more about positive examples.