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

想问一下WN18 和 WN18RR是什么关系 #76

Closed
xuefengDevelop opened this issue Jul 30, 2018 · 3 comments
Closed

想问一下WN18 和 WN18RR是什么关系 #76

xuefengDevelop opened this issue Jul 30, 2018 · 3 comments

Comments

@xuefengDevelop
Copy link

我是KG的小白,我想问一下WN18 和WN18RR 是什么关系?为什么WN18RR的mean rank, hit@10 relatively low。这个是来做sparse graph的测试吗?

提前感谢~

best

@ShulinCao
Copy link
Member

WN18 and FB15k suffer from test leakage through inverse relations: a large number of test triples can be obtained simply by inverting triples in the training set. For example, the test set frequently contains triples such as (s, hyponym, o) while the training set contains its inverse (o, hypernym, s). To create a dataset without this property, FB15k-237 was introduced – a subset of FB15k where inverse relations are removed. And similarly, WN18 was corrected by WN18RR.

@xuefengDevelop
Copy link
Author

Thank you for your reply, Shulin

It is very helpful!

Thanks again!

@jweihe
Copy link

jweihe commented Sep 30, 2020

thanks a lot

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

4 participants