UNQOVERing Stereotyping Biases via Underspecified Questions
EMNLP, pp. 3475-3489, 2020.
While language embeddings have been shown to have stereotyping biases, how these biases affect downstream question answering (QA) models remains unexplored. We present UNQOVER, a general framework to probe and quantify biases through underspecified questions. We show that a naive use of model scores can lead to incorrect bias estimates ...More
PPT (Upload PPT)