Update README.md
Browse files
README.md
CHANGED
|
@@ -74,19 +74,22 @@ The perplexity of Knesset-DictaBERT on the full test set is 6.60.
|
|
| 74 |
- **1-accuracy results**
|
| 75 |
|
| 76 |
Knesset-DictaBERT identified the correct token in the top-1 prediction in 52.55% of the cases.
|
|
|
|
| 77 |
The original DictaBERT model achieved a top-1 accuracy of 48.02%.
|
| 78 |
|
| 79 |
|
| 80 |
- **2-accuracy results**
|
| 81 |
|
| 82 |
Knesset-DictaBERT identified the correct token within the top-2 predictions in 63.07% of the cases.
|
| 83 |
-
|
|
|
|
| 84 |
|
| 85 |
|
| 86 |
- **5-accuracy results**
|
| 87 |
-
|
| 88 |
Knesset-DictaBERT identified the correct token within the top-5 predictions in 73.59% of the cases.
|
| 89 |
-
|
|
|
|
| 90 |
|
| 91 |
## Acknowledgments
|
| 92 |
This model is built upon the work of the Dicta team, and their contributions are gratefully acknowledged.
|
|
|
|
| 74 |
- **1-accuracy results**
|
| 75 |
|
| 76 |
Knesset-DictaBERT identified the correct token in the top-1 prediction in 52.55% of the cases.
|
| 77 |
+
|
| 78 |
The original DictaBERT model achieved a top-1 accuracy of 48.02%.
|
| 79 |
|
| 80 |
|
| 81 |
- **2-accuracy results**
|
| 82 |
|
| 83 |
Knesset-DictaBERT identified the correct token within the top-2 predictions in 63.07% of the cases.
|
| 84 |
+
|
| 85 |
+
The original DictaBERT model achieved a top-2 accuracy of 58.60%.
|
| 86 |
|
| 87 |
|
| 88 |
- **5-accuracy results**
|
| 89 |
-
|
| 90 |
Knesset-DictaBERT identified the correct token within the top-5 predictions in 73.59% of the cases.
|
| 91 |
+
|
| 92 |
+
The original DictaBERT model achieved a top-5 accuracy of 68.98%.
|
| 93 |
|
| 94 |
## Acknowledgments
|
| 95 |
This model is built upon the work of the Dicta team, and their contributions are gratefully acknowledged.
|