Understanding the Origins of Bias in Word Embeddings

Toronto Deep Learning Series Author Speaking For more details, visit https://tdls.a-i.science/events/2019-... Speaker: Marc Etienne Brunet (author) Facilitator: Waseem Gharbieh Abstract: The power of machine learning systems not only promises great technical progress, but risks societal harm. As a recent example, researchers have shown that popular word embedding algorithms exhibit stereotypical biases, such as gender bias. The widespread use of these algorithms in machine learning systems, from automated translation services to curriculum vitae scanners, can amplify stereotypes in important contexts. Although methods have been developed to measure these biases and alter word embeddings to mitigate their biased representations, there is a lack of understanding in how word embedding bias depends on the training data. In this work, we develop a technique for understanding the origins of bias in word embeddings.