fix(metrics): correct corpus_bleu reference structure in BleuScore#2889
Open
feiiiiii5 wants to merge 1 commit into
Open
fix(metrics): correct corpus_bleu reference structure in BleuScore#2889feiiiiii5 wants to merge 1 commit into
feiiiiii5 wants to merge 1 commit into
Conversation
References were passed as N streams of 1 segment each instead of 1 stream of N segments. sacrebleu zip(*references) truncated at length 1, so only the first sentence was evaluated — the rest silently discarded. Pass the full text as a single-segment corpus, consistent with ChrfScore. Fixes vibrantlabsai#2888.
Author
|
Note on the CI failures — neither is related to this change:
The fix itself is covered by the regression tests in the diff ( |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #2888. The references were passed as N streams of 1 segment each. sacrebleu's
zip(*references)truncated at length 1 → only the first sentence was ever evaluated. Passes full text as single-segment corpus (consistent with ChrfScore). Adds regression tests.