Name-based demographic inference and the unequal distribution of misrecognition
Academics and companies increasingly draw on large datasets to understand the social
world, and name-based demographic ascription tools are widespread for imputing …
world, and name-based demographic ascription tools are widespread for imputing …
[HTML][HTML] Avoiding bias when inferring race using name-based approaches
Racial disparity in academia is a widely acknowledged problem. The quantitative
understanding of racial-based systemic inequalities is an important step towards a more …
understanding of racial-based systemic inequalities is an important step towards a more …
[HTML][HTML] Estimating the success of re-identifications in incomplete datasets using generative models
While rich medical, behavioral, and socio-demographic data are key to modern data-driven
research, their collection and use raise legitimate privacy concerns. Anonymizing datasets …
research, their collection and use raise legitimate privacy concerns. Anonymizing datasets …
What's in a name? Reducing bias in bios without access to protected attributes
There is a growing body of work that proposes methods for mitigating bias in machine
learning systems. These methods typically rely on access to protected attributes such as …
learning systems. These methods typically rely on access to protected attributes such as …
Addressing census data problems in race imputation via fully Bayesian Improved Surname Geocoding and name supplements
Prediction of individuals' race and ethnicity plays an important role in studies of racial
disparity. Bayesian Improved Surname Geocoding (BISG), which relies on detailed census …
disparity. Bayesian Improved Surname Geocoding (BISG), which relies on detailed census …
Using first name information to improve race and ethnicity classification
I Voicu - Statistics and Public Policy, 2018 - Taylor & Francis
This article uses a recent first name list to develop an improvement to an existing Bayesian
classifier, namely the Bayesian Improved Surname Geocoding (BISG) method, which …
classifier, namely the Bayesian Improved Surname Geocoding (BISG) method, which …
MABEL: Attenuating gender bias using textual entailment data
Pre-trained language models encode undesirable social biases, which are further
exacerbated in downstream use. To this end, we propose MABEL (a Method for Attenuating …
exacerbated in downstream use. To this end, we propose MABEL (a Method for Attenuating …
Measuring model biases in the absence of ground truth
The measurement of bias in machine learning often focuses on model performance across
identity subgroups (such as man and woman) with respect to groundtruth labels. However …
identity subgroups (such as man and woman) with respect to groundtruth labels. However …
Lessons from archives: Strategies for collecting sociocultural data in machine learning
ES Jo, T Gebru - Proceedings of the 2020 conference on fairness …, 2020 - dl.acm.org
A growing body of work shows that many problems in fairness, accountability, transparency,
and ethics in machine learning systems are rooted in decisions surrounding the data …
and ethics in machine learning systems are rooted in decisions surrounding the data …
[HTML][HTML] A cross-verified database of notable people, 3500BC-2018AD
A new strand of literature aims at building the most comprehensive and accurate database
of notable individuals. We collect a massive amount of data from various editions of …
of notable individuals. We collect a massive amount of data from various editions of …