Fairness

Challenges in Detoxifying Language Models EMNLP 2021 Characterizing Fairness Over the Set of Good Models Under Selective Labels ICML 2021 Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation EMNLP 2021 Constructing a Fair Classifier with Generated Fair Data AAAI 2021 Constructing a Psychometric Testbed for Fair Natural Language Processing EMNLP 2021 Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation 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 DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks NeurIPS 2021 Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding EMNLP 2021 Detoxifying Language Models Risks Marginalizing Minority Voices NAACL 2021 Developing a Benchmark for Reducing Data Bias in Authorship Attribution EMNLP 2021 Discover the Unknown Biased Attribute of an Image Classifier ICCV 2021 Does enforcing fairness mitigate biases caused by subpopulation shift? NeurIPS 2021 Eliciting Bias in Question Answering Models through Ambiguity EMNLP 2021 Environment Inference for Invariant Learning ICML 2021 Evaluation of Summarization Systems across Gender, Age, and Race EMNLP 2021 Extending Challenge Sets to Uncover Gender Bias in Machine Translation: Impact of Stereotypical Verbs and Adjectives EMNLP 2021 Fair Attribute Classification Through Latent Space De-Biasing CVPR 2021 Fair Feature Distillation for Visual Recognition CVPR 2021 Fair Mixup: Fairness via Interpolation ICLR 2021 FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search ICCV 2021 Fairness and Bias in Online Selection ICML 2021 Fairness-aware Class Imbalanced Learning EMNLP 2021