debiaswe
Bias remover
Removes problematic gender bias from word embeddings to create more neutral representations.
Remove problematic gender bias from word embeddings.
244 stars
8 watching
90 forks
Language: Jupyter Notebook
last commit: over 3 years agodebiasgender-equalitynips-2016social-justiceword-embeddingsword2vec
Related projects:
| Repository | Description | Stars |
|---|---|---|
| An investigation into bias in image captioning systems using a dataset and a new model design to mitigate this bias | 13 | |
| A collection of useful Ember.js debugging functions. | 159 | |
| Enables better element selectors in Ember.js tests by removing unwanted attributes | 264 | |
| Debiasing techniques to minimize hallucinations in large visual language models | 75 | |
| A dataset of manually crafted sentence templates to evaluate the presence of gender bias in natural language processing systems | 70 | |
| Deconvolutes single-cell RNA-seq data from potential doublets to remove contamination | 69 | |
| Removes console statements from JavaScript code to strip debugging information | 251 | |
| This project provides a data proxy to evaluate bias in facial recognition systems across demographic groups. | 47 | |
| An implementation of a federated learning method to reduce domain bias in representation space, enabling improved knowledge transfer between clients and servers. | 22 | |
| Improves word embeddings by training with adversarial objectives | 118 | |
| Removes unnecessary whitespace from Handlebars templates to improve template performance and reduce file size. | 48 | |
| Quantifies 100 years of gender and ethnic stereotypes through word embeddings. | 161 | |
| A package that removes whitespace from strings and detects blank strings. | 12 | |
| A tool to update word vectors to align with linguistic constraints | 145 | |
| A PyTorch implementation of the skip-gram model for learning word embeddings. | 188 |