Closed bkj closed 5 years ago
We train and test the model using 1-N scoring, the same way as in Dettmers et al., 2018 (also see here): for each relation, we create an inverse by appending "_reverse" to the relation name. That way we are able to train and test only in one direction (desirable due to 1-N scoring), predicting both head and tail, because our dataset doesn't just contain (e_1, r, e_2), but also (e_2, r_reverse, e_1).
Ah ok -- makes sense I think. Thanks!
In the paper, you say
In the
evaluate
function, it looks like you score all possilbee_o
's given an(e_s, e_r)
tuple, then compute the rank of the truee_o
. So I see how you're doing1)
above, but are you actually doing2)
?Thanks! ~ Ben