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

RankEval: Will we run into folks running rank eval on a fully labelled corpus? #20441

Closed
MaineC opened this issue Sep 13, 2016 · 3 comments
Closed
Assignees
Labels
>feature :Search Relevance/Ranking Scoring, rescoring, rank evaluation. Team:Search Relevance Meta label for the Search Relevance team in Elasticsearch

Comments

@MaineC
Copy link

MaineC commented Sep 13, 2016

Question from @polyfractal I wonder if we'll run into folks who have an entirely labelled dataset (I'm thinking ML folks, not IR), who may be interested in metrics like f-score, AUC of ROC curve, etc? Just a thought for far-future discussions, no need to spend many cycles thinking about now. Sorta ties into what was mentioned about using scroll for bigger datasets, etc

@MaineC MaineC added >feature :Search Relevance/Ranking Scoring, rescoring, rank evaluation. labels Sep 13, 2016
@MaineC
Copy link
Author

MaineC commented Sep 13, 2016

While I myself like AUC of ROC curve and friends very much I wonder how for any practical purpose people would come up with a fully labelled corpus and store that inside of ES.

@cbuescher cbuescher self-assigned this Mar 13, 2018
@cbuescher
Copy link
Member

/cc @elastic/es-search-aggs

@cbuescher
Copy link
Member

Closing in favour of #29653 meta issue.

@javanna javanna added the Team:Search Relevance Meta label for the Search Relevance team in Elasticsearch label Jul 12, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
>feature :Search Relevance/Ranking Scoring, rescoring, rank evaluation. Team:Search Relevance Meta label for the Search Relevance team in Elasticsearch
Projects
None yet
Development

No branches or pull requests

3 participants