DeepAI AI Chat
Log In Sign Up

How Far Can It Go?: On Intrinsic Gender Bias Mitigation for Text Classification

01/30/2023
by   Ewoenam Tokpo, et al.
0

To mitigate gender bias in contextualized language models, different intrinsic mitigation strategies have been proposed, alongside many bias metrics. Considering that the end use of these language models is for downstream tasks like text classification, it is important to understand how these intrinsic bias mitigation strategies actually translate to fairness in downstream tasks and the extent of this. In this work, we design a probe to investigate the effects that some of the major intrinsic gender bias mitigation strategies have on downstream text classification tasks. We discover that instead of resolving gender bias, intrinsic mitigation techniques and metrics are able to hide it in such a way that significant gender information is retained in the embeddings. Furthermore, we show that each mitigation technique is able to hide the bias from some of the intrinsic bias measures but not all, and each intrinsic bias measure can be fooled by some mitigation techniques, but not all. We confirm experimentally, that none of the intrinsic mitigation techniques used without any other fairness intervention is able to consistently impact extrinsic bias. We recommend that intrinsic bias mitigation techniques should be combined with other fairness interventions for downstream tasks.

READ FULL TEXT

page 15

page 16

08/07/2019

Debiasing Embeddings for Reduced Gender Bias in Text Classification

(Bolukbasi et al., 2016) demonstrated that pretrained word embeddings ca...
10/26/2022

MABEL: Attenuating Gender Bias using Textual Entailment Data

Pre-trained language models encode undesirable social biases, which are ...
02/13/2023

Parameter-efficient Modularised Bias Mitigation via AdapterFusion

Large pre-trained language models contain societal biases and carry alon...
03/20/2023

Bias mitigation techniques in image classification: fair machine learning in human heritage collections

A major problem with using automated classification systems is that if t...
09/15/2021

Challenges in Detoxifying Language Models

Large language models (LM) generate remarkably fluent text and can be ef...
07/21/2022

The Birth of Bias: A case study on the evolution of gender bias in an English language model

Detecting and mitigating harmful biases in modern language models are wi...