|
--- |
|
license: cc-by-4.0 |
|
language: |
|
- ko |
|
- en |
|
tags: |
|
- translation |
|
--- |
|
## Model Details |
|
* Model Description: Fine-tuned facebook/nllb-200-distilled-600M model |
|
* Developed by: Juhwan Lee, Jisu Kim, TakSung Heo, and Minsu Jeong |
|
* Model Type: Translation |
|
* Language(s): |
|
* Source Language: English |
|
* Target Language: Korean |
|
* License: CC-BY-4.0 |
|
|
|
## Dataset |
|
* [AI-hub dataset](https://www.aihub.or.kr/) |
|
|
|
## BLEU Score |
|
* Before fine-tuning: 26.58 |
|
* After fine-tuning: 55.36 |
|
|
|
## Uses |
|
This model can be used for translation and text-to-text generation |
|
|
|
## Data Augmentation with backtranslation task |
|
You can exercise korean data augmentation task with python package [KoTAN](https://github.com/KoJLabs/KoTAN/tree/main) |
