As natural language processing (NLP) techniques are increasingly being used in various day-to-day applications, there is growing awareness that the decisions we as researchers and developers make about our data, methods, and algorithms have immense impact in shaping our social lives. In this talk, I will outline a growing body of research on ethical implications of NLP technologies, especially around fairness failures along various axes. I will discuss ways in which machine learned NLP models may reflect, propagate, and sometimes amplify social stereotypes about people, potentially harming already marginalized groups. I will cover research from our team at Google, as well as the larger research community on ways to detect and address these issues, and discuss the open challenges in this space.
Vinodkumar Prabhakaran is a Senior Research Scientist at Google working on issues around ethics, fairness and transparency in machine learning and natural language processing. Prior to Google, he was a postdoctoral researcher at Stanford University, and obtained his PhD in computer science from Columbia University. His prior research focused on building scalable ways using NLP to identify and address large-scale societal issues such as racial disparities in policing, workplace incivility, and online abuse. He has published over 40 articles in top-tier venues such as the PNAS, ACL, TACL, NAACL, EMNLP, and FAccT
