Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

NE is not replaced if it extends over serveral lines #55

Open
fexfl opened this issue Jan 3, 2025 · 0 comments
Open

NE is not replaced if it extends over serveral lines #55

fexfl opened this issue Jan 3, 2025 · 0 comments
Assignees
Labels
bug Something isn't working

Comments

@fexfl
Copy link
Collaborator

fexfl commented Jan 3, 2025

If an NE extends over several lines with "\r\n" etc. inbetween, it will not get replaced even if recognized by NER

  • Discovered in test email 297 from csv file
  • Batch size in test was 1
  • Original batch: 'François Chartier\r\nChargé de campagne Océans\r\nGreenpeace France\r\n[image]\r\n['
  • NER: [{'entity_group': 'PER', 'score': np.float32(0.999996), 'word': 'François Chartier', 'start': 0, 'end': 17}, {'entity_group': 'ORG', 'score': np.float32(0.9982297), 'word': 'Océans Greenpeace France', 'start': 38, 'end': 63}]
  • Pseudonymized batch: 'François Chartier\r\nChargé de campagne Océans\r\nGreenpeace France\r\n[image]\r\n['
@fexfl fexfl added the bug Something isn't working label Jan 3, 2025
@fexfl fexfl self-assigned this Jan 3, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

No branches or pull requests

1 participant