Gender Bias in Meta-Embeddings

05/19/2022
by   Masahiro Kaneko, et al.
6

Combining multiple source embeddings to create meta-embeddings is considered effective to obtain more accurate embeddings. Different methods have been proposed to develop meta-embeddings from a given set of source embeddings. However, the source embeddings can contain unfair gender bias, and the bias in the combination of multiple embeddings and debiasing it effectively have not been studied yet. In this paper, we investigate the bias in three types of meta-embeddings: (1) Multi-Source No-Debiasing: meta-embedding from multiple source embeddings without any debiasing. The experimental results show that meta-embedding amplifies the gender bias compared to those of input source embeddings; (2) Multi-Source Single-Debiasing: meta-embedding from multiple source embeddings debiased by a single method and it can be created in three ways: debiasing each source embedding, debiasing the learned meta-embeddings, and debiasing both source embeddings and meta-embeddings. The results show that debiasing both is the best in two out of three bias evaluation benchmarks; (3) Single-Source Multi-Debiasing: meta-embedding from the same source embedding debiased by different methods. It performed more effectively than its source embeddings debiased with a single method in all three bias evaluation benchmarks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/26/2022

Learning Meta Word Embeddings by Unsupervised Weighted Concatenation of Source Embeddings

Given multiple source word embeddings learnt using diverse algorithms an...
research
09/29/2019

Meta-Graph Based HIN Spectral Embedding: Methods, Analyses, and Insights

In this work, we propose to study the utility of different meta-graphs, ...
research
04/14/2018

Frustratingly Easy Meta-Embedding -- Computing Meta-Embeddings by Averaging Source Word Embeddings

Creating accurate meta-embeddings from pre-trained source embeddings has...
research
03/19/2020

A CSP implementation of the directed bigraph embedding problem

Directed bigraphs are a meta-model which generalises Milner's bigraphs b...
research
09/11/2019

Recognizing Variables from their Data via Deep Embeddings of Distributions

A key obstacle in automated analytics and meta-learning is the inability...
research
04/25/2022

A Survey on Word Meta-Embedding Learning

Meta-embedding (ME) learning is an emerging approach that attempts to le...
research
06/20/2020

MDR Cluster-Debias: A Nonlinear WordEmbedding Debiasing Pipeline

Existing methods for debiasing word embeddings often do so only superfic...

Please sign up or login with your details

Forgot password? Click here to reset