Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

WordBias: An Interactive Visual Tool for Discovering Intersectional Biases Encoded in Word Embeddings

Domain:

natural language processing

Record type:

software
Creator:
GhaHoqMue
Publisher:
arXiv
Host:avatar
Intersectional bias is a bias caused by an overlap of multiple social factors like gender, sexuality, race, disability, religion, etc. A recent study has shown that word embedding models can be laden with biases against intersectional groups like African American females, etc. The first step towards tackling such intersectional biases is to identify them. However, discovering biases against different intersectional groups remains a challenging task. In this work, we present WordBias, an interactive visual tool designed to explore biases against intersectional groups encoded in static word embeddings. Given a pretrained static word embedding, WordBias computes the association of each word along different groups based on race, age, etc. and then visualizes them using a novel interactive interface. Using a case study, we demonstrate how WordBias can help uncover biases against intersectional groups like Black Muslim Males, Poor Females, etc. encoded in word embedding. In addition, we also evaluate our tool using qualitative feedback from expert interviews. The source code for this tool can be publicly accessed for reproducibility at github.com. Accepted to ACM SIGCHI 2021 LBW

Visit

doi.orgarxiv.org

Tasks

embeddings

Tags

Computation and Language (cs.CL)Artificial Intelligence (cs.AI)Human-Computer Interaction (cs.HC)FOS: Computer and information sciencesFOS: Computer and information sciences

Licenses

arXiv.org perpetual, non-exclusive licensehttp://arxiv.org/licenses/nonexclusive-distrib/1.0/

Similar

Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like BiasesAraWEAT: Multidimensional Analysis of Biases in Arabic Word EmbeddingsVisual grounding of Interlingual Word embeddingsInteractive Refinement of Cross-Lingual Word EmbeddingsVisual Grounding of Inter-lingual Word-EmbeddingsAn Interactive Mobile Lecturing Tool for Empowering Distance Learners

Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases

With the starting point that implicit human biases are reflected in the statistical regularities of

AraWEAT: Multidimensional Analysis of Biases in Arabic Word Embeddings

Recent work has shown that distributional word vector spaces often encode human biases like sexism o

Visual grounding of Interlingual Word embeddings

Visual grounding of Interlingual Word embeddings

Poster presented at the Deep Learning Indaba 2022 by Wafaa Mohammed

Interactive Refinement of Cross-Lingual Word Embeddings

Cross-lingual word embeddings transfer knowledge between languages: models trained on high-resource

Visual Grounding of Inter-lingual Word-Embeddings

Visual grounding of Language aims at enriching textual representations of language with multiple sources of visual knowledge such as images and videos. Although visual grounding is an area of intense research, inter-lingual aspects of visual grounding have not rece

An Interactive Mobile Lecturing Tool for Empowering Distance Learners

Face-to-face learning is most prominent in higher education in developing countries of Africa, where