|
|
--- |
|
|
license: cc-by-4.0 |
|
|
language: |
|
|
- hu |
|
|
extra_gated_fields: |
|
|
Name: text |
|
|
Country: country |
|
|
Institution: text |
|
|
Institution Email: text |
|
|
Please specify your academic use case: text |
|
|
extra_gated_prompt: Our models are intended for academic use only. If you are not |
|
|
affiliated with an academic institution, please provide a rationale for using our |
|
|
models. Please allow us a few business days to manually review subscriptions. |
|
|
--- |
|
|
|
|
|
## 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 |
|
|
|
|
|
```py |
|
|
from transformers import AutoTokenizer, AutoModelForSequenceClassification |
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained("poltextlab/HunMediBERT3") |
|
|
model = AutoModelForSequenceClassification.from_pretrained("poltextlab/HunMediBERT3") |
