Comparing Methods for Mitigating Gender Bias in Word Embedding

Date

2023-01-03

Contributor

Advisor

Department

Instructor

Depositor

Speaker

Researcher

Consultant

Interviewer

Narrator

Transcriber

Annotator

Journal Title

Journal ISSN

Volume Title

Publisher

Volume

Number/Issue

Starting Page

722

Ending Page

Alternative Title

Abstract

Word embedding captures the semantic and syntactic meaning of words into dense vectors. It contains biases learning from data that include constructs, cultural stereotypes, and inequalities of the society. Many methods for removing bias in traditional word embedding have been proposed. In this study we use the original GloVe word embedding and perform a comparison among debiasing methods built on top of GloVe in order to determine which methods perform the best removing bias. We have defined half-sibling regression, repulsion attraction neutralization GloVe method and compared it with gender-preserving, gender-neutral GloVe method and other debiased methods. According to our results, no methods outperform in all the analyses and completely remove gender information from gender neutral words. Furthermore, all the debiasing methods perform better than the original GloVe.

Description

Keywords

Accountability, Evaluation, and Obscurity of AI Algorithms, gender bias, glove, natural language processing, word embedding

Citation

Extent

10

Format

Geographic Location

Time Period

Related To

Proceedings of the 56th Hawaii International Conference on System Sciences

Related To (URI)

Table of Contents

Rights

Attribution-NonCommercial-NoDerivatives 4.0 International

Rights Holder

Local Contexts

Email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.