Shirin Seyedsalehi

PhD Student (Alumni)

Toronto Metropolitan University

Shirin Seyedsalehi is a former PhD student and alumna of the Human-Centered Machine Intelligence Lab at Toronto Metropolitan University. Her research focused on bias mitigation in information retrieval systems and neural ranking models.

Interests

Machine Learning
Information Retrieval
Bias Mitigation
Neural Networks

Latest

A Regularization Framework for Gender Bias Mitigation in Dense Neural Rankers
Refairmulate: A Benchmark Dataset for Gender-Fair Query Reformulations
Self-Paced Fair Ranking with Loss as a Proxy for Bias
A contrastive neural disentanglement approach for query performance prediction
Bias-Aware Curriculum Sampling For Fair Ranking
Gender disentangled representation learning in neural rankers
Understanding and Mitigating Gender Bias in Information Retrieval Systems
De-biasing relevance judgements for fair ranking
Don't Raise Your Voice, Improve Your Argument: Learning to Retrieve Convincing Arguments
Neural disentanglement of query difficulty and semantics
Understanding and mitigating gender bias in information retrieval systems
A Light-Weight Strategy for Restraining Gender Biases in Neural Rankers
A Light-Weight Strategy for Restraining Gender Biases in Neural Rankers
A Neural Approach to Forming Coherent Teams in Collaboration Networks
A Neural Approach to Forming Coherent Teams in Collaboration Networks
Addressing gender-related performance disparities in neural rankers
Bias-aware Fair Neural Ranking for Addressing Stereotypical Gender Biases
Gender fairness in information retrieval systems
Matches made in heaven: Toolkit and large-scale datasets for supervised query reformulation
On the orthogonality of bias and utility in ad hoc retrieval