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

Word '' is sometimes tagged by NER #53

Open
fexfl opened this issue Dec 26, 2024 · 1 comment
Open

Word '' is sometimes tagged by NER #53

fexfl opened this issue Dec 26, 2024 · 1 comment
Assignees
Labels
bug Something isn't working

Comments

@fexfl
Copy link
Collaborator

fexfl commented Dec 26, 2024

Encountered bug while testing batching sizes.

  • Spacy model: French
  • Batching size: 4
  • Debugging NER output: [{'entity_group': 'MISC', 'score': np.float32(0.9299379), 'word': 'ESZ', 'start': 41, 'end': 44}, {'entity_group': 'PER', 'score': np.float32(0.98025304), 'word': 'lino.silva1', 'start': 49, 'end': 60}, {'entity_group': 'PER', 'score': np.float32(0.9931357), 'word': '', 'start': 140, 'end': 141}]
  • File: Re reunião agendada para o dia 24 de abril 2024-04-17T17_39_49+02 00.eml
@fexfl fexfl added the bug Something isn't working label Dec 26, 2024
@fexfl fexfl self-assigned this Dec 26, 2024
@fexfl
Copy link
Collaborator Author

fexfl commented Jan 5, 2025

Also occurs in test email 250

  • Spacy model: French
  • Batching size: -1
  • Debugging NER output: {'entity_group': 'ORG', 'score': np.float32(0.8815035), 'word': '', 'start': 1749, 'end': 1750}

Issue only seems to occur for large batching sizes, batch size 1 has worked for both emails. Issue is not related to spacy model language, since this email is in french.

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