Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

What's the rational behind ReLU(s + o) − (s − o)? #6

Open
KimRasak opened this issue Sep 14, 2023 · 0 comments
Open

What's the rational behind ReLU(s + o) − (s − o)? #6

KimRasak opened this issue Sep 14, 2023 · 0 comments

Comments

@KimRasak
Copy link

Practically, the entity-predicate matching is shown below:
$F(s, o) ≈ p$
where $F(s, o)$ is defined as: $ReLU(s + o) − (s − o)^2$

I don't see the reason why the equation must be this way. If (s-o) refers to the difference between the 2 vectors, (s+o) refers to the combination of the 2 vectors, what does the equation $F(s, o)$ means?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant