-
Notifications
You must be signed in to change notification settings - Fork 35
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
Model Performance #47
Comments
In the Spider dataset paper (Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task by Tao Yu et al.) they created their own model. I think it also applies to this model to some extend: "The performance decreases as the database has more foreign keys. The first reason is because the model has to choose column and table names from many candidates in a complex database schema. Second, a complex database schema presents a great challenge for the model to capture the relationship between different tables with foreign keys." |
So what could be the possible solutions for the bigger databases? |
Better mapping between potential solutions and actual solutions. |
Can you suggest some implementations, that can help?
…On Fri, 3 Sep, 2021, 3:02 pm Reinier Koops, ***@***.***> wrote:
Better mapping between potential solutions and actual solutions.
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
<#47 (comment)>, or
unsubscribe
<https://github.com/notifications/unsubscribe-auth/AMZS64HDXXS4PAL7IUEZUC3UACI3DANCNFSM5DILTZMA>
.
|
I don't think there is a solution to it yet, really. |
Thanks alot for your time! |
Hi @OhadRubin any suggestions on this? |
The model is working fine for smaller DBs. But when there are multiple level of foreign key connections it seems to struggle
Why is it so, any reason?
The text was updated successfully, but these errors were encountered: