Closed VictorMatt01 closed 2 years ago
Here hard_negative_weight is the log of the hard negative weight (alpha in Table 7).
I guess I have the same question, what's the point of having summands that you multiply by 0? Like [0.0] * (cos_sim.size(-1) - z1_z3_cos.size(-1))
. Wont's this weights
tensor always boil down to just [z3_weight]
?
[0.0] * x will create an array of size x with all values as 0.
So this question is about the algorithm when it uses 3 sentences as input: In the code on github the following "weight is used" when computing the final cos_sim score, but apperantly this score is 0. I can't really find an explanation for it in the paper and i was wondering how the cos_sim would change if the weight is changed (both in positive and negative direction)