Add warning about METEOR version and flag-induced score variance#677
Merged
lhoestq merged 1 commit intohuggingface:mainfrom Nov 14, 2025
Merged
Add warning about METEOR version and flag-induced score variance#677lhoestq merged 1 commit intohuggingface:mainfrom
lhoestq merged 1 commit intohuggingface:mainfrom
Conversation
This pull request adds a call-out block at the top of `evaluate/metrics/meteor/README.md` to inform users about significant score discrepancies in METEOR evaluations. Variations up to ±10 points can occur due to differences between versions 1.0 and 1.5, as well as the use of specific flags (`-l`, `-norm`, `-vOut`). By highlighting this issue, users are encouraged to specify the Java package version and document the flags used to ensure reproducibility. The information is based on findings from Lübbers (2024), available at [https://github.com/cluebbers/Reproducibility-METEOR-NLP](https://github.com/cluebbers/Reproducibility-METEOR-NLP).
Contributor
Author
lhoestq
approved these changes
Nov 14, 2025
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This pull request adds a call-out block at the top of
evaluate/metrics/meteor/README.mdto inform users about significant score discrepancies in METEOR evaluations. Variations up to ±10 points can occur due to differences between versions 1.0 and 1.5, as well as the use of specific flags (-l,-norm,-vOut). By highlighting this issue, users are encouraged to specify the Java package version and document the flags used to ensure reproducibility. The information is based on findings from Lübbers (2024), available at https://github.com/cluebbers/Reproducibility-METEOR-NLP.