You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
During training, there may exist some false negatives.
For example, the correct entity happens to appear in another triple within the same batch.
We filter out such entities with a binary mask.
If a <h, r, t> triple is true according to the training data,
we do not consider t as a negative.
We use a mask to implement this mechanism.
I would like to ask, what do triplet masks and other masks in the code do? Looking forward to your answer!
The text was updated successfully, but these errors were encountered: