Data Science Seminar
A Visual tour of Bias Mitigation
Jeff Phillips
A Visual tour of Bias Mitigation
| When | Friday, August 27, 2021, 2:00 PM – 3:00 PM (MT) |
|---|---|
| Where | MEB 3147 |
Abstract
Word vector embeddings have been shown to contain and amplify biases in data they are extracted from. Consequently, many techniques have been proposed to identify, mitigate, and attenuate these biases in word representations. In this talk, I will review a collection of state-of-the-art debiasing techniques. To aid this, we provide an open source web-based visualization tool VERB (Visualization of Embedding Representations for deBiasing) and offer hands-on experience in exploring the effects of these debiasing techniques on the geometry of high-dimensional word vectors. To help understand how various debiasing techniques change the underlying geometry, I will show how to decompose each technique into interpretable sequences of primitive operations and study their effect on the word vectors using dimensionality reduction and interactive visual exploration.
Speaker
Tags: deep learning fairness & ethics natural language processing visualization
Part of the Data Science Seminar. Something wrong on this page? Edit _data/talks/2021-08-27-jeff-phillips.toml.