About
A transformer-based model for named entity recognition for Polish. The model was trained on the train part of the KPWr corpus to recognize 82 categories of NE.
Evaluation summary
precision recall f1-score support
micro avg 0.7803 0.8033 0.7916 17711
macro avg 0.7921 0.8033 0.7932 17711
Detailed results can be found in the test_results.txt file.
Author
Michał Marcińczuk marcinczuk@gmail.com
License
- Downloads last month
- 10
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.