|
--- |
|
|
|
license: cc-by-nc-4.0 |
|
language: |
|
- hu |
|
- en |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: Hun_Eng_RoBERTa_base_Plain |
|
results: |
|
- task: |
|
type: text-classification |
|
metrics: |
|
- type: accuracy |
|
value: 0.75 (hu) / 0.65 (en) |
|
- type: f1 |
|
value: 0.74 (hu) / 0.64 (en) |
|
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-base` model for Hungarian and English, trained on datasets provided by the National Tax and Customs Administration - Hungary (NAV) and translated versions of the same dataset using Google Translate API. |
|
|
|
## Intended uses & limitations |
|
|
|
The model is designed to classify sentences as either "comprehensible" or "not comprehensible" (according to Plain Language guidelines): |
|
* **Label_0** - "comprehensible" - The sentence is in Plain Language. |
|
* **Label_1** - "not comprehensible" - The sentence is **not** in Plain Language. |
|
|
|
## Training |
|
|
|
Fine-tuned version of the original `xlm-roberta-base` model, trained on a dataset of Hungarian legal and administrative texts. The model was also trained on the translated version of this dataset (via Google Translate API) for English classification. |
|
|
|
## Eval results |
|
|
|
### Hungarian Results: |
|
| Class | Precision | Recall | F1-Score | |
|
| ----- | --------- | ------ | -------- | |
|
| **Comprehensible / Label_0** | **0.82** | **0.62** | **0.70** | |
|
| **Not comprehensible / Label_1** | **0.71** | **0.88** | **0.78** | |
|
| **accuracy** | | | **0.75** | |
|
| **macro avg** | **0.77** | **0.75** | **0.74** | |
|
| **weighted avg** | **0.76** | **0.75** | **0.74** | |
|
|
|
### English Results: |
|
| Class | Precision | Recall | F1-Score | |
|
| ----- | --------- | ------ | -------- | |
|
| **Comprehensible / Label_0** | **0.70** | **0.50** | **0.58** | |
|
| **Not comprehensible / Label_1** | **0.63** | **0.80** | **0.70** | |
|
| **accuracy** | | | **0.65** | |
|
| **macro avg** | **0.66** | **0.65** | **0.64** | |
|
| **weighted avg** | **0.66** | **0.65** | **0.64** | |
|
|
|
## Usage |
|
|
|
```python |
|
from transformers import AutoTokenizer, AutoModelForSequenceClassification |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("uvegesistvan/Hun_Eng_RoBERTa_base_Plain") |
|
model = AutoModelForSequenceClassification.from_pretrained("uvegesistvan/Hun_Eng_RoBERTa_base_Plain") |
|
``` |
|
|
|
|