metadata
license: cc-by-nc-4.0
language:
- hu
metrics:
- accuracy
- f1
model-index:
- name: Hun_RoBERTa_large_Plain
results:
- task:
type: text-classification
metrics:
- type: accuracy
value: 0.79
- type: f1
value: 0.79
widget:
- text: >-
A tanúsítvány meghatározott adatainak a 2008/118/EK irányelv IV. fejezete
szerinti szállításához szükséges adminisztratív okmányban...
example_title: Incomprehensible
- text: >-
Az AEO-engedély birtokosainak listáján – keresésre – megjelenő
információk: az engedélyes neve, az engedélyt kibocsátó ország...
example_title: Comprehensible
Model description
Cased fine-tuned XLM-RoBERTa-large model for Hungarian, trained to classify sentences based on their plain language comprehensibility.
Intended uses & limitations
The model is designed to classify sentences as either "comprehensible" or "not comprehensible" (according to Plain Language guidelines):
- Label_0 - "comprehensible"
- Label_1 - "not comprehensible"
Training
Fine-tuned version of the original xlm-roberta-large model, trained on a dataset of Hungarian legal and administrative texts.
Eval results
| Class | Precision | Recall | F-Score |
|---|---|---|---|
| Comprehensible / Label_0 | 0.76 | 0.86 | 0.81 |
| Not comprehensible / Label_1 | 0.83 | 0.72 | 0.77 |
| accuracy | 0.79 | ||
| macro avg | 0.80 | 0.79 | 0.79 |
| weighted avg | 0.79 | 0.79 | 0.79 |
Usage
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("uvegesistvan/Hun_RoBERTa_large_Plain")
model = AutoModelForSequenceClassification.from_pretrained("uvegesistvan/Hun_RoBERTa_large_Plain")