Gender Disentangled Representation Learning in Neural Rankers
Talk, ACML 2024, Hanoi, Vietnam
Paper presentation at ACML2024.
Talks and presentations
Gender Disentangled Representation Learning in Neural Rankers
Talk, CSE Seminar Series, McMaster University, Hamilton, ON, Canada
This seminar introduced a disentanglement-based framework for reducing gender bias in neural ranking systems and discussed empirical findings on real-world search datasets.
Understanding and Mitigating Gender Bias in Information Retrieval Systems
Talk, EECS Seminar Series, York University, Toronto, ON, Canada
A presentation exploring bias sources in neural retrieval models and practical debiasing strategies within large-scale IR pipelines.
Understanding and Mitigating Gender Bias in Information Retrieval Systems
Talk, Department of Computer Science and Software Engineering (CSSE), Concordia University, Montreal, QC, Canada
This invited talk discussed sources of gender bias in information retrieval systems and introduced recent methods for mitigation and evaluation.
Gender Biases in Neural Rankers
Talk, Microsoft Research, Toronto, ON, Canada
An invited research talk focusing on quantifying and mitigating gender-related performance disparities in modern neural rankers.
Stereotypical Gender Biases in Information Retrieval Systems
Talk, Information Retrieval Group, Radboud University, Online
A research talk highlighting how stereotypical gender associations emerge in ranking models and discussing data-driven approaches for mitigation.