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 is the range of score_conv1["score"]? #20

Open
qye-supplyframe opened this issue Mar 26, 2024 · 1 comment
Open

What is the range of score_conv1["score"]? #20

qye-supplyframe opened this issue Mar 26, 2024 · 1 comment

Comments

@qye-supplyframe
Copy link

What is the range for scores computed by both methods? I saw in another post that, evaluation score by SummaC-ZS is from [-1, 1] or [0, 1] depending on the argument of use_con. How about the range of SummaC-Cov? What is the meaning of score values? Are they the probability of getting summary from the reference document?

@karrtikiyer
Copy link

I think output of SummaC-Cov is probability of binary classification model from 0 to 1.
I kinds of tells us the chances of summary being inconsistent with the document provided.
I believe the authors suggest we used balanced accuracy scores https://scikit-learn.org/1.5/modules/generated/sklearn.metrics.balanced_accuracy_score.html for all our datapoints to determine the overall accuracy of the model, instead of looking at a particular data point in isolation.

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

2 participants