N
Nithum Thain
Researcher at Google
Publications - 41
Citations - 2612
Nithum Thain is an academic researcher from Google. The author has contributed to research in topics: Computer science & Conversation. The author has an hindex of 14, co-authored 36 publications receiving 1589 citations. Previous affiliations of Nithum Thain include Simon Fraser University & Queen's University.
Papers
More filters
Proceedings ArticleDOI
Measuring and Mitigating Unintended Bias in Text Classification
TL;DR: A new approach to measuring and mitigating unintended bias in machine learning models is introduced, using a set of common demographic identity terms as the subset of input features on which to measure bias.
Proceedings ArticleDOI
Ex Machina: Personal Attacks Seen at Scale
TL;DR: A method that combines crowdsourcing and machine learning to analyze personal attacks at scale is developed and illustrated, and an evaluation method for a classifier in terms of the aggregated number of crowd-workers it can approximate is shown.
Posted Content
Ex Machina: Personal Attacks Seen at Scale
TL;DR: In this article, a method that combines crowdsourcing and machine learning to analyze personal attacks at scale is presented, which shows that the majority of personal attacks on Wikipedia are not the result of a few malicious users, nor primarily the consequence of allowing anonymous contributions from unregistered users.
Posted Content
Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification
TL;DR: A suite of threshold-agnostic metrics are introduced that provide a nuanced view of unintended bias in Machine Learning, by considering the various ways that a classifier’s score distribution can vary across designated groups.
Proceedings Article
Fairness without Demographics through Adversarially Reweighted Learning
Preethi Lahoti,Alex Beutel,Jilin Chen,Kang Lee,Flavien Prost,Nithum Thain,Xuezhi Wang,Ed H. Chi +7 more
TL;DR: Adversarially Reweighted Learning (ARLWang et al. as mentioned in this paper proposed an adversarial reweighting approach to improve Max-Min fairness in machine learning.