This repository was archived by the owner on Apr 8, 2025. It is now read-only.
This repository was archived by the owner on Apr 8, 2025. It is now read-only.
Assign correct probabilities to NER predictions #658
Description
In TokenClassificationHead.formatted_preds( ), we filter out spans for non-entity words, but we do not yet filter out probabilities of non-entity words. This leads to a misalignment of predictions and probabilities.
Metadata
Metadata
Assignees
Labels
No labels