Probabilistic Bias Mitigation in Word Embeddings

10/31/2019
by   Hailey James-Sorenson, et al.
0

It has been shown that word embeddings derived from large corpora tend to incorporate biases present in their training data. Various methods for mitigating these biases have been proposed, but recent work has demonstrated that these methods hide but fail to truly remove the biases, which can still be observed in word nearest-neighbor statistics. In this work we propose a probabilistic view of word embedding bias. We leverage this framework to present a novel method for mitigating bias which relies on probabilistic observations to yield a more robust bias mitigation algorithm. We demonstrate that this method effectively reduces bias according to three separate measures of bias while maintaining embedding quality across various popular benchmark semantic tasks

READ FULL TEXT
research
07/21/2021

Using Adversarial Debiasing to Remove Bias from Word Embeddings

Word Embeddings have been shown to contain the societal biases present i...
research
06/30/2020

OSCaR: Orthogonal Subspace Correction and Rectification of Biases in Word Embeddings

Language representations are known to carry stereotypical biases and, as...
research
06/30/2021

Fair Visual Recognition in Limited Data Regime using Self-Supervision and Self-Distillation

Deep learning models generally learn the biases present in the training ...
research
05/23/2023

Detecting and Mitigating Indirect Stereotypes in Word Embeddings

Societal biases in the usage of words, including harmful stereotypes, ar...
research
03/28/2022

The SAME score: Improved cosine based bias score for word embeddings

Over the last years, word and sentence embeddings have established as te...
research
03/11/2021

DebIE: A Platform for Implicit and Explicit Debiasing of Word Embedding Spaces

Recent research efforts in NLP have demonstrated that distributional wor...
research
11/15/2022

Mind Your Bias: A Critical Review of Bias Detection Methods for Contextual Language Models

The awareness and mitigation of biases are of fundamental importance for...

Please sign up or login with your details

Forgot password? Click here to reset