Update README.md
Browse files
README.md
CHANGED
|
@@ -12,23 +12,28 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 12 |
|
| 13 |
# Clickbait1
|
| 14 |
|
| 15 |
-
This model is a fine-tuned version of [microsoft/Multilingual-MiniLM-L12-H384](https://huggingface.co/microsoft/Multilingual-MiniLM-L12-H384) on the
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
- Loss: 0.0257
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
| 21 |
-
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## Intended uses & limitations
|
| 24 |
|
| 25 |
-
|
|
|
|
|
|
|
| 26 |
|
| 27 |
## Training and evaluation data
|
| 28 |
|
| 29 |
-
|
| 30 |
|
| 31 |
## Training procedure
|
|
|
|
| 32 |
|
| 33 |
### Training hyperparameters
|
| 34 |
|
|
|
|
| 12 |
|
| 13 |
# Clickbait1
|
| 14 |
|
| 15 |
+
This model is a fine-tuned version of [microsoft/Multilingual-MiniLM-L12-H384](https://huggingface.co/microsoft/Multilingual-MiniLM-L12-H384) on the [Webis-Clickbait-17](https://zenodo.org/record/5530410) dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
- Loss: 0.0257
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
| 21 |
+
MiniLM is a distilled model from the paper "MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers".
|
| 22 |
+
|
| 23 |
+
We fine tune this model to evaluate (regression) the clickbait level of title news.
|
| 24 |
|
| 25 |
## Intended uses & limitations
|
| 26 |
|
| 27 |
+
Model looks like the model described in the paper [Predicting Clickbait Strength in Online Social Media](https://aclanthology.org/2020.coling-main.425/) by Indurthi Vijayasaradhi, Syed Bakhtiyar, Gupta Manish, Varma Vasudeva.
|
| 28 |
+
|
| 29 |
+
The model was trained with english titles.
|
| 30 |
|
| 31 |
## Training and evaluation data
|
| 32 |
|
| 33 |
+
We trained the model with the official training data for the chalenge (clickbait17-train-170630.zip (894 MiB, 19538 posts), plus another set that was just available after the end of the challenge (clickbait17-train-170331.zip (157 MiB, 2459 posts).
|
| 34 |
|
| 35 |
## Training procedure
|
| 36 |
+
Code can be find in [Github](https://github.com/caush/Clickbait).
|
| 37 |
|
| 38 |
### Training hyperparameters
|
| 39 |
|