Update README.md
Browse files
README.md
CHANGED
|
@@ -7,14 +7,15 @@ license: mit
|
|
| 7 |
datasets:
|
| 8 |
- textdetox/multilingual_paradetox
|
| 9 |
language:
|
| 10 |
-
- ru
|
| 11 |
- en
|
| 12 |
- ar
|
| 13 |
- am
|
| 14 |
- zh
|
|
|
|
|
|
|
| 15 |
- es
|
|
|
|
| 16 |
- de
|
| 17 |
-
- hi
|
| 18 |
metrics:
|
| 19 |
- chrf
|
| 20 |
pipeline_tag: text2text-generation
|
|
@@ -22,14 +23,17 @@ pipeline_tag: text2text-generation
|
|
| 22 |
|
| 23 |
# mT5-XL Detoxification Baseline
|
| 24 |
|
| 25 |
-
This is a baseline detoxification model trained on released parallel corpus of toxic texts [MultiParadetox](https://huggingface.co/datasets/textdetox/multilingual_paradetox)
|
| 26 |
|
| 27 |
|
| 28 |
## Model Details
|
| 29 |
|
| 30 |
-
The base model for this fine-tune is mT5-XL.
|
| 31 |
|
| 32 |
### Model Description
|
| 33 |
|
| 34 |
<!-- Provide a longer summary of what this model is. -->
|
| 35 |
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
datasets:
|
| 8 |
- textdetox/multilingual_paradetox
|
| 9 |
language:
|
|
|
|
| 10 |
- en
|
| 11 |
- ar
|
| 12 |
- am
|
| 13 |
- zh
|
| 14 |
+
- uk
|
| 15 |
+
- hi
|
| 16 |
- es
|
| 17 |
+
- ru
|
| 18 |
- de
|
|
|
|
| 19 |
metrics:
|
| 20 |
- chrf
|
| 21 |
pipeline_tag: text2text-generation
|
|
|
|
| 23 |
|
| 24 |
# mT5-XL Detoxification Baseline
|
| 25 |
|
| 26 |
+
This is a baseline detoxification model trained on released parallel corpus (dev part) of toxic texts [MultiParadetox](https://huggingface.co/datasets/textdetox/multilingual_paradetox)
|
| 27 |
|
| 28 |
|
| 29 |
## Model Details
|
| 30 |
|
| 31 |
+
The base model for this fine-tune is [mT5-XL](https://huggingface.co/google/mt5-xl).
|
| 32 |
|
| 33 |
### Model Description
|
| 34 |
|
| 35 |
<!-- Provide a longer summary of what this model is. -->
|
| 36 |
|
| 37 |
+
## Citation
|
| 38 |
+
|
| 39 |
+
The model is developed as a baseline for [TextDetox CLEF-2024](https://pan.webis.de/clef24/pan24-web/text-detoxification.html) shared task.
|