{{ message }}
Repository navigation
The GLiNER side-by-side covers English and the single-pass case - #309
Merged
Merged
Conversation
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Signed-off-by: Wayland Yang <wayland0916@gmail.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Follow-up to #305. Adds the English translations of the pharma and tech corpora with matching answer keys, and rewrites the GLiNER section of the bench README as a full report: conditions, four label settings (answer-key classes, 965 classes in batches, 965 classes in one pass), Chinese and English tables, timings, and the reading.
The new rows: with all 965 labels in a single pass GLiNER finds 0, 0, 4 and 2 entities across the four corpora, because the labels fill the encoder window and the text is truncated away. On English its recall is complete in the batched setting while type precision still falls to 13/20 and 4/14 against 19/20 and 12/13 for the pipeline after type resolution.
🤖 Generated with Claude Code