These tools and metrics are designed to help AI actors develop and use trustworthy AI systems and applications that respect human rights and are fair, transparent, explainable, robust, secure and safe.
RAN-Debias: Repulsion-Attraction-Neutralization Debias
This paper presents RAN-Debias, a gender de-biasing methodology which eliminates the bias present in a word vector and alters the spatial distribution of its neighboring vectors, achieving a bias-free setting while maintaining minimal semantic offset.
This paper also proposes a new bias evaluation metric – Gender-based Illicit Proximity Estimate (GIPE), which measures the extent of undue proximity in word vectors resulting from the presence of gender-based predilections. Experiments based on a suite of evaluation metrics show that RAN-Debias significantly outperforms the state-of-the-art in reducing proximity bias (GIPE) by at least 42.02%. It also reduces direct bias, adding minimal semantic disturbance, and achieves the best performance in a downstream application task (coreference resolution).
This method not only mitigates direct bias of a word, but also reduces its associations with other words that arise from gender-based predilections.
About the tool
You can click on the links to see the associated tools
Developing organisation(s):
Tool type(s):
Objective(s):
Impacted stakeholders:
Country of origin:
Type of approach:
Maturity:
Target groups:
Target users:
Stakeholder group:
Benefits:
Geographical scope:
Required skills:
Technology platforms:
Use Cases
Would you like to submit a use case for this tool?
If you have used this tool, we would love to know more about your experience.
Add use case