Gender Bias in Word Embeddings: A Case Study on NLP

July 21, 2016

An investigation by researchers from Boston University and Microsoft Research, New England uncovered gender bias in popular word embedding techniques for Natural Language Processing (NLP). This AI incident maps to the Govern function in HISPI Project Cerebellum Trusted AI Model (TAIM). Ready to help shape trustworthy and responsible AI? JOIN US
Alleged deployer
microsoft-research, boston-university
Alleged developer
microsoft-research, google, boston-university
Alleged harmed parties
women, minority-groups

Source

Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/12

Data source

Incident data is from the AI Incident Database (AIID).

When citing the database as a whole, please use:

McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. In Proceedings of the Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-21). Virtual Conference.

Pre-print on arXiv · Database snapshots & citation guide

We use weekly snapshots of the AIID for stable reference. For the official suggested citation of a specific incident, use the “Cite this incident” link on each incident page.