Commit 41b8e4e7 authored by Sparsh Jauhari's avatar Sparsh Jauhari 💬
Browse files

Update README.md with details of debiase.py

parent a2172afe
......@@ -55,7 +55,7 @@ gdown https://drive.google.com/uc?id=1Lj_RteEF_wAEsENZBLQYGBLMY99VfI5j
## Usage
The runnable `train.py` can be used to train the models and predict then on test set while
`predict.py` can be used for single predictions. All the results, plots and evaluations can be seen in the `bios_bias.ipynb`. `debiasing...............` takes care of the debiasing.
`predict.py` can be used for single predictions. All the results, plots and evaluations can be seen in the `bios_bias.ipynb`. `debiase.py` takes care of the debiasing.
#### Training and Predictions
```bash
......@@ -109,5 +109,12 @@ python predict
>`--pred_all_models` - yes for all or no for the specific one
#### Debiasing of embeddings
........................................................write!!!!!!!!!!!!!!
The `debias.py` is used to debias the word2Vec embeddings trained on our dataset of medical domain. The code in the file is a refactored version of the code that can be found at:<br /> https://github.com/tolga-b/debiaswe/tree/10277b23e187ee4bd2b6872b507163ef4198686b/debiaswe <br />
The code uses
>`definitional_pairs.json` - The ten pairs of words used to define the gender direction. <br />
>`gender_specific_full.json` . A list of 1441 gender-specific words <br />
The source of the files is :<br /> https://github.com/tolga-b/debiaswe/tree/10277b23e187ee4bd2b6872b507163ef4198686b/data <br />
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment