Fairness

Data-Driven Methods for Balancing Fairness and Efficiency in Ride-Pooling IJCAI 2021 Debiasing Evaluations That Are Biased by Evaluations AAAI 2021 Debiasing Methods in Natural Language Understanding Make Bias More Accessible EMNLP 2021 Debiasing Pre-trained Contextualised Embeddings EACL 2021 DebIE: A Platform for Implicit and Explicit Debiasing of Word Embedding Spaces EACL 2021 Decision Making with Differential Privacy under a Fairness Lens IJCAI 2021 Defending Multimodal Fusion Models Against Single-Source Adversaries CVPR 2021 Detecting Community Sensitive Norm Violations in Online Conversations EMNLP 2021 Detecting Cross-Geographic Biases in Toxicity Modeling on Social Media EMNLP 2021 Detecting Inappropriate Messages on Sensitive Topics that Could Harm a Company’s Reputation EACL 2021 Detoxifying Language Models Risks Marginalizing Minority Voices NAACL 2021 Developing a Benchmark for Reducing Data Bias in Authorship Attribution EMNLP 2021 Dictionary-based Debiasing of Pre-trained Word Embeddings EACL 2021 Differentially Private and Fair Deep Learning: A Lagrangian Dual Approach AAAI 2021 Differentially Private Empirical Risk Minimization under the Fairness Lens NeurIPS 2021 Directional Bias Amplification ICML 2021 Disentangling Document Topic and Author Gender in Multiple Languages: Lessons for Adversarial Debiasing EACL 2021 District-Fair Participatory Budgeting AAAI 2021 Ditto: Fair and Robust Federated Learning Through Personalization ICML 2021 Diverse Adversaries for Mitigating Bias in Training EACL 2021 Does enforcing fairness mitigate biases caused by subpopulation shift? NeurIPS 2021 Does Social Pressure Drive Persuasion in Online Fora? EMNLP 2021 Don’t Discard All the Biased Instances: Investigating a Core Assumption in Dataset Bias Mitigation Techniques EMNLP 2021 Double Perturbation: On the Robustness of Robustness and Counterfactual Bias Evaluation NAACL 2021 Dynamically Disentangling Social Bias from Task-Oriented Representations with Adversarial Attack NAACL 2021