Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,41 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
datasets:
|
| 4 |
+
- anilguven/turkish_news_dataset
|
| 5 |
+
language:
|
| 6 |
+
- tr
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
- f1
|
| 10 |
+
tags:
|
| 11 |
+
- news
|
| 12 |
+
- classification
|
| 13 |
+
- turkish
|
| 14 |
+
- xlm-roberta
|
| 15 |
+
---
|
| 16 |
+
### Information
|
| 17 |
+
This model was developed/finetuned for news classification task for the Turkish Language. This model was finetuned via news dataset. This dataset contains 7 classes: economy, magazine, sport, politics, technology, health, and events.
|
| 18 |
+
|
| 19 |
+
- LABEL_0: economy
|
| 20 |
+
- LABEL_1: magazine
|
| 21 |
+
- LABEL_2: health
|
| 22 |
+
- LABEL_3: politics
|
| 23 |
+
- LABEL_4: sports
|
| 24 |
+
- LABEL_5: technology
|
| 25 |
+
- LABEL_6: events
|
| 26 |
+
|
| 27 |
+
### Model Sources
|
| 28 |
+
- **Dataset:** https://huggingface.co/datasets/anilguven/turkish_news_dataset
|
| 29 |
+
- **Paper:** peer review (Springer)
|
| 30 |
+
- **Finetuned from model::** https://huggingface.co/Overfit-GM/xlm-roberta-large-turkish-offensive
|
| 31 |
+
|
| 32 |
+
### Preprocessing
|
| 33 |
+
You must apply removing stopwords, stemming, or lemmatization process for Turkish.
|
| 34 |
+
|
| 35 |
+
### Results
|
| 36 |
+
- Accuracy: %95.595
|
| 37 |
+
- F1-score: %95.586
|
| 38 |
+
|
| 39 |
+
### Citation
|
| 40 |
+
BibTeX:
|
| 41 |
+
Peer review process
|