Transform references for sacrebleu #520
Merged
Conversation
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
lhoestq
reviewed
Aug 20, 2020
There was a problem hiding this comment.
Thanks for reporting this !
Indeed sacrebleu expected this unusual format as input...
I think it would be better to check that all the references have the same length rather than cropping to the minimum length. If one length doesn't match the others, we should probably raise an error. What do you think ?
|
I think I agree @lhoestq so I pushed a change. |
thomwolf
approved these changes
Aug 20, 2020
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.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.
Currently it is impossible to use sacrebleu when len(predictions) != the number of references per prediction (very uncommon), due to a strange format expected by sacrebleu. If one passes in the data to
nlp.metric.compute()in sacrebleu format,nlpthrows an error due to mismatching lengths between predictions and references. If one uses a more standard format where predictions and references are lists of the same length, sacrebleu throws an error.This PR transforms reference data in a more standard format into the unusual format expected by sacrebleu.