Model description
Cased fine-tuned BERT model for Hungarian, trained on 2738 (manually annotated) online news sentences.
Intended uses & limitations
The model can be used as any other (cased) BERT model. It has been tested recognizing guilt at the sentence level, where:
0_label: none
1_label: guilt
Results
precision recall f1-score support
0 0.98 0.95 0.97 133
1 0.96 0.98 0.97 141
accuracy 0.97 274
macro avg 0.97 0.97 0.97 274
weighted avg 0.97 0.97 0.97 274
- Downloads last month
- 6