uvegesistvan
commited on
Commit
•
fbff7f3
1
Parent(s):
8d45dd6
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,54 @@
|
|
1 |
---
|
2 |
license: cc-by-nc-4.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: cc-by-nc-4.0
|
3 |
+
language:
|
4 |
+
- hu
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
model-index:
|
8 |
+
- name: huBERTPlain
|
9 |
+
results:
|
10 |
+
- task:
|
11 |
+
type: text-classification
|
12 |
+
metrics:
|
13 |
+
- type: accuracy
|
14 |
+
value: 0.73
|
15 |
+
|
16 |
---
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
Cased fine-tuned BERT model for Hungarian, trained on a dataset provided by National Tax and Customs Administration - Hungary (NAV): Public Accessibilty Programme.
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
The model can be used as any other (cased) BERT model. It has been tested recognizing "accessible" and "original" sentences, where:
|
25 |
+
* "accessible" - "Label_1": sentence, that can be considered as comprehensible (regarding to Plain Language directives)
|
26 |
+
* "original" - "Label_0": sentence, that needs to rephrased in order to follow Plain Language Guidelines.
|
27 |
+
|
28 |
+
## Training
|
29 |
+
|
30 |
+
Fine-tuned version of the original huBERT model (`SZTAKI-HLT/hubert-base-cc`), trained on information materials provided by NAV linguistic experts.
|
31 |
+
|
32 |
+
## Eval results
|
33 |
+
|
34 |
+
| Class | Precision | Recall | F-Score |
|
35 |
+
|-----|------------|------------|------|
|
36 |
+
| **Original / Label_0** | **0.71** | **0.79** | **0.75**|
|
37 |
+
| **Accessible / Label_1** | **0.76** | **0.67** | **0.71**|
|
38 |
+
| **accuracy** | | | **0.73**|
|
39 |
+
| **macro avg** | **0.74** | **0.73** | **0.73**|
|
40 |
+
| **weighted avg** | **0.74** | **0.73** | **0.73**|
|
41 |
+
|
42 |
+
### BibTeX entry and citation info
|
43 |
+
|
44 |
+
If you use the model, please cite the following papers:
|
45 |
+
|
46 |
+
Bibtex:
|
47 |
+
```bibtex
|
48 |
+
@PhDThesis{ Uveges:2023,
|
49 |
+
author = {{"U}veges, Istv{\'a}n},
|
50 |
+
title = {A k{\"o}z{\'e}rthet{\"o}s{\'e}g lehet{\"o}s{\'e}gei a jogi dom{\'e}n sz{\"o}vegeiben},
|
51 |
+
year = {2023},
|
52 |
+
school = {Szegedi Tudom\'anyegyetem}
|
53 |
+
}
|
54 |
+
```
|