Salesforce researchers claim new method mitigates AI models’ gender bias

Researchers at Salesforce and the University of Virginia have proposed a new way to mitigate gender bias in word embeddings, the word representations used to train AI models to summarize, translate languages, and perform other prediction tasks. The team says correcting for certain regularities — like word frequency in large data sets — allows their method to “purify” the embeddings prior to inference, removing potentially gendered words.

https://venturebeat.com/2020/07/01/salesforce-researchers-claim-new-method-mitigates-ai-models-gender-bias/