NeurIPS 2021

Timezone: »

An Interactive Visual Demo of Bias Mitigation Techniques for Word Representations

Archit Rathore · Sunipa Dev · Vivek Srikumar · Jeff M Phillips · Yan Zheng · Michael Yeh · Junpeng Wang · Wei Zhang · Bei Wang

Fri Dec 10 09:05 AM -- 09:20 AM (PST) @

in Demonstrations 4 »

Event URL: https://tdavislab.github.io/verb/ »

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 tutorial, we will review a collection of state-of-the-art debiasing techniques. To aid this, we provide an open source web-based visualization tool 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, we decompose each technique into interpretable sequences of primitive operations, and study their effect on the word vectors using dimensionality reduction and interactive visual exploration.

Author Information

Archit Rathore (University of Utah)

Sunipa Dev (Google Research)

Computing Innovation Fellow 2020, Research Assistant at University of Utah, Postdoctoral Fellow at UCLA starting Jan 2020. Research interests are Responsible and Interpretable AI, NLP and Algorithmic Fairness.

Vivek Srikumar (University of Utah)

Jeff M Phillips (University of Utah)

Yan Zheng (Visa Research)

Michael Yeh (Visa Research)

Junpeng Wang (VISA Research)

Wei Zhang (Visa Research)

Bei Wang (University of Utah)

Bei Wang is an assistant professor at the School of Computing, a faculty member in the Scientific Computing and Imaging (SCI) Institute, and an adjunct assistant professor in the Department of Mathematics, University of Utah. She received her Ph.D. in Computer Science from Duke University. Her research interests include data visualization, topological data analysis, computational topology, computational geometry, machine learning, and data mining. She has worked on projects related to computational biology, bioinformatics, and robotics. Some of her current research activities draw inspirations from topology, geometry, and machine learning, in studying vector fields, tensor fields, high-dimensional point clouds, networks, and multivariate ensembles.