Model description
Experimental model for sentiment classification in case of Hungarian news.
Intended uses & limitations
- Label "0": Neutral
- Label "1": Positive
- Label "2": Negative
Training
Fine-tuned version of the original huBERT model (SZTAKI-HLT/hubert-base-cc
), trained on news texts.
Eval results
Class | Precision | Recall | F-Score |
---|---|---|---|
Neutral | 0.7 | 0.35 | 0.47 |
Positive | 0.74 | 0.85 | 0.79 |
Negative | 0.89 | 0.91 | 0.9 |
accuracy | 0.82 | ||
macro avg | 0.77 | 0.7 | 0.72 |
weighted avg | 0.81 | 0.82 | 0.81 |
Usage
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("poltextlab/HunMediBERT3")
model = AutoModelForSequenceClassification.from_pretrained("poltextlab/HunMediBERT3")