Closed natuhvnh closed 2 years ago
Hi,
In this form, xi+ is the entailment of xi. Can you elaborate more on "few of those appear in the mini-batch"?
I mean that somehow hj+ is similar to hi+ (both are entailment of hi. But here hj+ is in the denominator, dose it effect the performance?
Hi,
Hj+ is not the entailment sentence for hi (it is the entailment for hj). It is supposed to be different from hi.
Hi, I have a question about the loss function calculation:
It means that we treat x(i) and x(j) similar to x(i) and its contradiction hypotheses ?
If yes, the loss function will not work well in case x(i) has many entialment hypothesis in the datasets and few of those appear in the mini-batch ?