Black is to Criminal as Caucasian is to Police:Detecting and Removing Multiclass Bias in Word Embeddings

04/03/2019
by   Thomas Manzini, et al.
0

Online texts -- across genres, registers, domains, and styles -- are riddled with human stereotypes, expressed in overt or subtle ways. Word embeddings, trained on these texts, perpetuate and amplify these stereotypes, and propagate biases to machine learning models that use word embeddings as features. In this work, we propose a method to debias word embeddings in multiclass settings such as race and religion, extending the work of (Bolukbasi et al., 2016) from the binary setting, such as binary gender. Next, we propose a novel methodology for the evaluation of multiclass debiasing. We demonstrate that our multiclass debiasing is robust and maintains the efficacy in standard NLP tasks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/09/2020

Joint Multiclass Debiasing of Word Embeddings

Bias in Word Embeddings has been a subject of recent interest, along wit...
research
03/24/2018

Near-lossless Binarization of Word Embeddings

Is it possible to learn binary word embeddings of arbitrary size from th...
research
04/13/2021

On the interpretation and significance of bias metrics in texts: a PMI-based approach

In recent years, the use of word embeddings has become popular to measur...
research
11/24/2020

Unequal Representations: Analyzing Intersectional Biases in Word Embeddings Using Representational Similarity Analysis

We present a new approach for detecting human-like social biases in word...
research
06/25/2021

A Source-Criticism Debiasing Method for GloVe Embeddings

It is well-documented that word embeddings trained on large public corpo...
research
11/25/2019

Towards robust word embeddings for noisy texts

Research on word embeddings has mainly focused on improving their perfor...
research
04/06/2023

Affect as a proxy for literary mood

We propose to use affect as a proxy for mood in literary texts. In this ...

Please sign up or login with your details

Forgot password? Click here to reset