Welcome to the WEFE documentation!

WEFE: The Word Embeddings Fairness Evaluation Framework is an open source library for measuring and mitigating bias in word embedding models.

The following pages contain the documentation about WEFE: how to install the package, how to use it and how to contribute, as well as the detailed API documentation and extensive examples.

Getting Started

• About
  • Motivation and objectives
  • Similar Packages
  • Measurement Framework
  • Metrics
  • Relevant Papers
  • Citation
  • Roadmap
  • License
  • Team
  • Contact
  • Acknowledgments
• Quick Start
  • Download and setup
  • Run your first Query

Documentation

• Bias Measurement
  • Run a Query
  • Run Query Arguments
  • Out of Vocabulary Words
  • Word Preprocessors
  • Running multiple Queries
  • Aggregating Results
  • Model Ranking
  • Correlating Rankings
• Bias Mitigation
  • Hard Debias
  • Multiclass Hard Debias
• Loading Embeddings From Different Sources
  • Create a example query
  • Load from Gensim API
  • Using Gensim Load
  • Flair
• Contributing
  • Get the repository
  • Testing
  • Build the documentation
  • How to implement your own metric
  • Mitigation Method Implementation Guide
• WEFE API
  • WordEmbeddingModel
  • Query
  • Metrics
  • Debias
  • Dataloaders

Examples

• Replication of Previous Studies
  • WEAT Replication
  • RNSB Replication
• Rank Word Embeddings Fairness using several Metrics and Queries

Repository

You can find the project repository at the following link: WEFE repository on Github.