Commit
•
6d66f92
1
Parent(s):
2b5f963
update image link
Browse files
README.md
CHANGED
|
@@ -26,6 +26,6 @@ Based on a few experimentations, we observed that this model could produce biase
|
|
| 26 |
|
| 27 |
For instance, for sentences like `This film was filmed in COUNTRY`, this binary classification model will give radically different probabilities for the positive label depending on the country (0.89 if the country is France, but 0.08 if the country is Afghanistan) when nothing in the input indicates such a strong semantic shift. In this [colab](https://colab.research.google.com/gist/ageron/fb2f64fb145b4bc7c49efc97e5f114d3/biasmap.ipynb), [Aurélien Géron](https://twitter.com/aureliengeron) made an interesting map plotting these probabilities for each country.
|
| 28 |
|
| 29 |
-
<img src="map.jpeg" alt="Map of positive probabilities per country." width="500"/>
|
| 30 |
|
| 31 |
We strongly advise users to thoroughly probe these aspects on their use-cases in order to evaluate the risks of this model. We recommend looking at the following bias evaluation datasets as a place to start: [WinoBias](https://huggingface.co/datasets/wino_bias), WinoGender, [Stereoset](https://huggingface.co/datasets/stereoset).
|
| 26 |
|
| 27 |
For instance, for sentences like `This film was filmed in COUNTRY`, this binary classification model will give radically different probabilities for the positive label depending on the country (0.89 if the country is France, but 0.08 if the country is Afghanistan) when nothing in the input indicates such a strong semantic shift. In this [colab](https://colab.research.google.com/gist/ageron/fb2f64fb145b4bc7c49efc97e5f114d3/biasmap.ipynb), [Aurélien Géron](https://twitter.com/aureliengeron) made an interesting map plotting these probabilities for each country.
|
| 28 |
|
| 29 |
+
<img src="https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english/resolve/main/map.jpeg" alt="Map of positive probabilities per country." width="500"/>
|
| 30 |
|
| 31 |
We strongly advise users to thoroughly probe these aspects on their use-cases in order to evaluate the risks of this model. We recommend looking at the following bias evaluation datasets as a place to start: [WinoBias](https://huggingface.co/datasets/wino_bias), WinoGender, [Stereoset](https://huggingface.co/datasets/stereoset).
|