Debiasing Word Embeddings

Linear Digressions

• Episode: Debiasing Word Embeddings
• Website: Linear Digressions
• Feed URL: http://feeds.feedburner.com/udacity-linear-digressions?format=xml
• Duration: 00:18:20
• Published: 2017-12-18 03:31

When we covered the Word2Vec algorithm for embedding words, we mentioned parenthetically that the word embeddings it produces can sometimes be a little bit less than ideal--in particular, gender bias from our society can creep into the embeddings and give results that are sexist. For example, occupational words like "doctor" and "nurse" are more highly aligned with "man" or "woman," which can create problems because these word embeddings are used in algorithms that help people find information or make decisions. However, a group of researchers has released a new paper detailing ways to de-bias the embeddings, so we retain gender info that's not particularly problematic (for example, "king" vs. "queen") while correcting bias.