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

Pretrained lookup_embedder doesn't work for reciprocal_relations_model #190

Closed
nluedema opened this issue Mar 6, 2021 · 3 comments
Closed
Assignees

Comments

@nluedema
Copy link
Contributor

nluedema commented Mar 6, 2021

There is a problem with using pretrained relation embeddings for the lookup_embedder when using the reciprocal_relations_model. Only the first half (the non-reciprocal relation embeddings) are used, while the second half is ignored.

The problem seems to be with the function _intersect_ids_with_pretrained_embedder in kge_model.py.

elif "relation_embedder" in self.configuration_key:
    self_ids = self.dataset.relation_ids()
    pretrained_ids = pretrained_embedder.dataset.relation_ids()

The above code block only gets the first half of the relation id's and ignores the second half that was created by the reciprocal_relations_model.

@rgemulla
Copy link
Member

rgemulla commented Mar 7, 2021

Thanks for reporting this bug! @AdrianKs: Will you have a look?

@AdrianKs
Copy link
Collaborator

AdrianKs commented Mar 8, 2021

yes, I will have a look

@AdrianKs
Copy link
Collaborator

fixed in #191

This issue was closed.
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

3 participants