How to Remove Gender Bias in Machine Learning Models: NLP and Word Embeddings

Written by jay-gupta | Published 2020/09/07
Tech Story Tags: natural-language-processing | deep-learning | gender-bias | word-embeddings | machine-learning | artificial-intelligence | neural-networks | hackernoon-top-story

TLDR How to Remove Gender Bias in Machine Learning Models: NLP and Word Embeddings. This article provides a review and the arguments made by Bolukbasi et al. in the paper “Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embedings”. In this article, we’ll be using Word2Vec for all the examples. To remove the gender bias, we need to identify the gender dimension (A word embedding consists of hundreds of dimensions)via the TL;DR App
no story
Written by jay-gupta | CS Major at NTU, Singapore
Published by HackerNoon on 2020/09/07
ABOUTHow hackers start their afternoons. We publish tech stories and build publishing software.

READEntirely free library read by hundreds of millions to learn anything about any technology.

WRITEHackerNoon elevates quality technology writing far and wide across the interwebs.

PARTNERHackerNoon works directly with tech companies to place ads by content relevancy