90 citations · 188 across the 13 of their papers we have counts for
4 papers · 1 filter
Algorithmic Gender Prediction Is Illegitimate, But Gender Imputation Can Yield Valid Measurements
Evan Dong, Angelina Wang
Machine learning ethics researchers and critical HCI scholars have argued that algorithmically predicting gender is wrong. At the same time, other researchers rely on predicted gen…
Taxonomizing and Measuring Representational Harms: A Look at Image Tagging
Jared Katzman, Angelina Wang, Morgan Scheuerman +4
In this paper, we examine computational approaches for measuring the "fairness" of image tagging systems, finding that they cluster into five distinct categories, each with its own…
Measuring Representational Harms in Image Captioning
Angelina Wang, Solon Barocas, Kristen Laird +1
Previous work has largely considered the fairness of image captioning systems through the underspecified lens of "bias." In contrast, we present a set of techniques for measuring f…
The Limits of Global Inclusion in AI Development
Alan Chan, Chinasa T. Okolo, Zachary Terner +1
Those best-positioned to profit from the proliferation of artificial intelligence (AI) systems are those with the most economic power. Extant global inequality has motivated Wester…