[go: nahoru, domu]
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.

Sign up for GitHub

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

Jump to bottom

About predicted relevance score in NDCG #13

Closed
zlh-source opened this issue Nov 30, 2023 · 1 comment
Closed

About predicted relevance score in NDCG #13

zlh-source opened this issue Nov 30, 2023 · 1 comment

Comments

@zlh-source
Copy link

Hello, the listwise method can generate the relevance order of candidate documents instead of the relevance score. When you calculate ndcg, how do you input your predicted relevance score into the ndcg function?

I looked at your code and it seems that if the k-th relevant document is ranked, then its predicted relevance score is 1/k ?
@sunnweiwei
Copy link
Owner

Hi. The calculation of NDCG doesn't utilize predicted relevance scores. The code you mentioned is adapted from https://github.com/castorini/pyserini/blob/master/pyserini/eval/trec_eval.py.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@zlh-source @sunnweiwei