Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases.

Wei Guo Aylin Caliskan

Published in: AIES (2021)

Keyphrases

co occurrence
high dimensional data
data sets
neural network
learning algorithm
probability distribution
low dimensional
n gram
data distribution
manifold learning
human behavior
spatial distribution
bayesian models