|
--- |
|
license: apache-2.0 |
|
--- |
|
Model description Cased fine-tuned BERT model for English, trained on (manually annotated) Hungarian parliamentary speeches scraped from parlament.hu, and translated with Google Translate API. |
|
|
|
Intended uses & limitations The model can be used as any other (cased) BERT model. It has been tested recognizing positive, negative, and neutral sentences in (parliamentary) pre-agenda speeches, where: |
|
|
|
'Label_0': Negative 'Label_1': Neutral 'Label_2': Positive |
|
|
|
Training The fine-tuned version of the original bert-base-cased model (bert-base-cased), trained on HunEmPoli corpus, translated with Google Translate API. |
|
|
|
Intended uses & limitations: The model can be used as any other (cased) BERT model. |
|
|
|
Eval results |
|
|
|
precision recall f1-score support |
|
|
|
0 0.87 0.87 0.87 1118 |
|
1 1.00 0.26 0.41 35 |
|
2 0.78 0.82 0.80 748 |
|
|
|
accuracy 0.83 1901 |
|
macro avg 0.88 0.65 0.69 1901 |
|
weighted avg 0.84 0.83 0.83 1901 |
|
|
