Upload README.md
Browse files
README.md
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
datasets:
|
4 |
+
- Abdou/dz-sentiment-yt-comments
|
5 |
+
language:
|
6 |
+
- ar
|
7 |
+
metrics:
|
8 |
+
- f1
|
9 |
+
- accuracy
|
10 |
+
library_name: transformers
|
11 |
+
---
|
12 |
+
# BERT Models Fine-tuned on Algerian Dialect Sentiment Analysis
|
13 |
+
These are different BERT models (BERT Arabic models are initialized from [AraBERT](https://huggingface.co/aubmindlab/bert-large-arabertv02)) fine-tuned on the [Algerian Dialect Sentiment Analysis](https://huggingface.co/datasets/Abdou/dz-sentiment-yt-comments) dataset. The dataset contains 50,016 comments from YouTube videos in Algerian dialect. The models are evaluated on the testing set:
|
14 |
+
|
15 |
+
|
16 |
+
| Model Version | No. of Parameters | Training Time | F1-Score | Accuracy |
|
17 |
+
| ------------------- | ----------------- | -------------- | -------- | -------- |
|
18 |
+
| LSTM | ~4 M | 3 min | 0.7399 | 0.7445 |
|
19 |
+
| Bi-LSTM | ~4.3 M | 6 min 35 s | 0.7380 | 0.7437 |
|
20 |
+
| [BERT Base](https://huggingface.co/bert-base-uncased) | ~109.5 M | 33 min 20 s | 0.6979 | 0.7500 |
|
21 |
+
| [BERT Large](https://huggingface.co/bert-large-uncased) | ~335.1 M | 1 h 50 min | 0.6976 | 0.7484 |
|
22 |
+
| [BERT Arabic Mini](https://huggingface.co/Abdou/arabert-mini-algerian) | ~11.6 M | 2 min 40 s | 0.7057 | 0.7527 |
|
23 |
+
| [BERT Arabic Medium](https://huggingface.co/Abdou/arabert-medium-algerian) | ~42.1 M | 11 min 25 s | 0.7521 | 0.7860 |
|
24 |
+
| [BERT Arabic Base](https://huggingface.co/Abdou/arabert-base-algerian) | ~110.6 M | 34 min 19 s | 0.7688 | 0.8002 |
|
25 |
+
| **[BERT Arabic Large](https://huggingface.co/Abdou/arabert-large-algerian)** | **~336.7 M** | **1 h 53 min** | **0.7838** | **0.8174** |
|