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

Questions about the test set #17

Open
luoxindi opened this issue Nov 2, 2022 · 4 comments
Open

Questions about the test set #17

luoxindi opened this issue Nov 2, 2022 · 4 comments

Comments

@luoxindi
Copy link

luoxindi commented Nov 2, 2022

Hello, I would like to know how to get the correct answers of the questions in test set and their corresponding sparql statements? Do I only need to upload my model to the website you provided to get the results each time when I change the model? In other words, how do I get this test set with complete information?

@entslscheia
Copy link
Collaborator

entslscheia commented Nov 2, 2022

Hi Xindi,

We didn't release the labels for test set on purpose for fair comparison (just like many other QA benchmarks did). To evaluate your model on the test set, you can follow the official instructions here. It's actually quite simple; you only need to submit the predictions rather than the model per se. To debug your model locally, we strongly recommend you using the dev set of GrailQA, which shares a similar distribution with the test set in terms of generalization levels.

Feel free to let me know if you have any further questions!

Best,
Yu

@luoxindi
Copy link
Author

luoxindi commented Nov 2, 2022

I got it, thanks

@lgxccc
Copy link

lgxccc commented Jul 30, 2023

May I ask why this website is not accessible now. I was able to access this website a few months ago. May I ask if you can log in to this website now?

@entslscheia
Copy link
Collaborator

@lgxccc Looks like Codalab was down days ago but it's back now. You can also directly send your predictions to my email if you want

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