Main content

Detection and Mitigation of Gender Bias in Natural Language Processing

Show full item record

Title: Detection and Mitigation of Gender Bias in Natural Language Processing
Author: Dawkins, Hillary
Department: School of Computer Science
Program: Computational Sciences
Advisor: McCuaig, JudiGillis, Daniel
Abstract: This thesis contributes to our collective understanding of how gender bias arises in natural language processing systems, provides new detection and measurement tools, and develops mitigation methods. More specifically, we quantify and reduce bias within pre-trained computational resources, both word embeddings and language models, such that unwanted outcomes produced by the system are mitigated. Unwanted outcomes include any system prediction that is unduly influenced by the presence of gender words or the latent concept of gender in language (e.g. when an NLP system is unable to predict that ``she" refers to a doctor). On the theme of detection, we make two new observations on how gender bias can manifest in system predictions. Firstly, gender words are shown to carry either marked or default values. Default values may pass through systems undetected, while marked values influence prediction outcomes. Secondly, unwanted latent inferences are detected, due to a shared gender association. We contribute two new test sets, and one enhanced test set, for the purpose of gender bias detection. On the theme of mitigation, we develop successful debiasing strategies applied to both types of pre-trained resources.
Date: 2023-02
Terms of Use: All items in the Atrium are protected by copyright with all rights reserved unless otherwise indicated.
Related Publications: Hillary Dawkins. 2021. Marked Attribute Bias in Natural Language Inference. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 4214–4226, Online. Association for Computational Linguistics. DOI: 10.18653/v1/2021.findings-acl.369

Files in this item

Files Size Format View
Dawkins_Hillary_202302_PhD.pdf 684.2Kb PDF View/Open

This item appears in the following Collection(s)

Show full item record

The library is committed to ensuring that members of our user community with disabilities have equal access to our services and resources and that their dignity and independence is always respected. If you encounter a barrier and/or need an alternate format, please fill out our Library Print and Multimedia Alternate-Format Request Form. Contact us if you’d like to provide feedback:  (email address)