Gender disentangled representation learning in neural rankers

Shirin Seyedsalehi, Sara Salamat, Negar Arabzadeh, Sajad Ebrahimi, Morteza Zihayat, Ebrahim Bagheri
January 2025

Abstract

This paper presents gender disentangled representation learning approaches for neural rankers, addressing bias issues in information retrieval systems.

Type
Journal article
Publication
Machine Learning

This work introduces gender disentanglement techniques for reducing bias in neural ranking systems.

Gender Disentanglement Representation Learning Neural Rankers Bias Mitigation Information Retrieval
Morteza Zihayat
Morteza Zihayat
Principal Investigator

Dr. Morteza Zihayat is an Assistant Professor in the School of Information Technology Management at Toronto Metropolitan University and the Director of the Human-Centered Machine Intelligence Lab.