Update README.md
Browse files
README.md
CHANGED
|
@@ -27,6 +27,15 @@ with torch.no_grad():
|
|
| 27 |
# [1 0]
|
| 28 |
```
|
| 29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
## Training procedure
|
| 31 |
|
| 32 |
### Training
|
|
@@ -85,4 +94,14 @@ Metrics only on `astromis/WCL_Wiki_Ru`:
|
|
| 85 |
accuracy 0.92 985
|
| 86 |
macro avg 0.92 0.92 0.92 985
|
| 87 |
weighted avg 0.92 0.92 0.92 985
|
| 88 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
# [1 0]
|
| 28 |
```
|
| 29 |
|
| 30 |
+
## Preprocessing
|
| 31 |
+
|
| 32 |
+
- lower_string
|
| 33 |
+
- remove_punct
|
| 34 |
+
- remove_latin
|
| 35 |
+
- swap_enter_to_space
|
| 36 |
+
- collapse_spaces
|
| 37 |
+
- strip_string
|
| 38 |
+
|
| 39 |
## Training procedure
|
| 40 |
|
| 41 |
### Training
|
|
|
|
| 94 |
accuracy 0.92 985
|
| 95 |
macro avg 0.92 0.92 0.92 985
|
| 96 |
weighted avg 0.92 0.92 0.92 985
|
| 97 |
+
```
|
| 98 |
+
|
| 99 |
+
# Citation
|
| 100 |
+
|
| 101 |
+
@article{Popov2025TransferringNL,
|
| 102 |
+
title={Transferring Natural Language Datasets Between Languages Using Large Language Models for Modern Decision Support and Sci-Tech Analytical Systems},
|
| 103 |
+
author={Dmitrii Popov and Egor Terentev and Danil Serenko and Ilya Sochenkov and Igor Buyanov},
|
| 104 |
+
journal={Big Data and Cognitive Computing},
|
| 105 |
+
year={2025},
|
| 106 |
+
url={https://api.semanticscholar.org/CorpusID:278179500}
|
| 107 |
+
}
|