Commit
•
a47cc1c
1
Parent(s):
69ed3b8
Model Description
Browse files
README.md
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
**Amharic Hate Speech Detection using Fine-tuned mBERT**
|
| 2 |
+
|
| 3 |
+
**Model description**
|
| 4 |
+
|
| 5 |
+
This model was created by finetuning the mBERT model for the downstream task of Hate speech detection for the Amharic language.
|
| 6 |
+
The initial mBERT model used for finetuning is Davlan/bert-base-multilingual-cased-finetuned-amharic which was provided by Davlan on Huggingface.
|
| 7 |
+
The model was fine-tuned using HuggingFace's Trainer API. The final result of the finetuning has an F1-score of 0.9172 and an accuracy of 91.59%.
|
| 8 |
+
|
| 9 |
+
**Dataset description**
|
| 10 |
+
The finetuning was done on an Amharic Dataset that was made available by Mendeley Data (https://data.mendeley.com/datasets/ymtmxx385m). It has a size of 30,000 rows.
|
| 11 |
+
|
| 12 |
+
**Other**
|
| 13 |
+
The Google Colab notebook is made available on my GitHub. Check this path https://github.com/amengemeda/ISproject-2/blob/main/mBERT/Amharic_Hate_Speech_detection_using_mBERT_(Trainer_API).ipynb
|