• Publications
  • Influence
Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods
TLDR
A data-augmentation approach is demonstrated that, in combination with existing word-embedding debiasing techniques, removes the bias demonstrated by rule-based, feature-rich, and neural coreference systems in WinoBias without significantly affecting their performance on existing coreference benchmark datasets. Expand
Learning Gender-Neutral Word Embeddings
TLDR
A novel training procedure for learning gender-neutral word embeddings that preserves gender information in certain dimensions of word vectors while compelling other dimensions to be free of gender influence is proposed. Expand
Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints
TLDR
This work proposes to inject corpus-level constraints for calibrating existing structured prediction models and design an algorithm based on Lagrangian relaxation for collective inference that results in almost no performance loss for the underlying recognition task but decreases the magnitude of bias amplification. Expand
Gender Bias in Contextualized Word Embeddings
TLDR
It is shown that a state-of-the-art coreference system that depends on ELMo inherits its bias and demonstrates significant bias on the WinoBias probing corpus and two methods to mitigate such gender bias are explored. Expand
Mitigating Gender Bias in Natural Language Processing: Literature Review
TLDR
This paper discusses gender bias based on four forms of representation bias and analyzes methods recognizing gender bias in NLP, and discusses the advantages and drawbacks of existing gender debiasing methods. Expand
Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations
TLDR
It is shown that trained models significantly amplify the association of target labels with gender beyond what one would expect from biased datasets, and an adversarial approach is adopted to remove unwanted features corresponding to protected variables from intermediate representations in a deep neural network. Expand
Fairness-Aware Explainable Recommendation over Knowledge Graphs
TLDR
This paper analyzes different groups of users according to their level of activity, and finds that bias exists in recommendation performance between different groups, and proposes a fairness constrained approach via heuristic re-ranking to mitigate this unfairness problem in the context of explainable recommendation over knowledge graphs. Expand
Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer
TLDR
This paper creates a multilingual dataset for bias analysis and proposes several ways for quantifying bias in multilingual representations from both the intrinsic and extrinsic perspectives, and shows that the magnitude of bias in the mult bilingual representations changes differently when the authors align the embeddings to different target spaces. Expand
Deep Neural Network with Joint Distribution Matching for Cross-Subject Motor Imagery Brain-Computer Interfaces
TLDR
The source subject's data are explored to perform calibration for target subjects and a deep neural network with joint distribution matching for zero-training motor imagery BCI is proposed, which explores both marginal and joint distribution adaptation to alleviate distribution discrepancy across subjects and obtain effective and generalized features in an aligned common space. Expand
LOGAN: Local Group Bias Detection by Clustering
TLDR
LOGAN, a new bias detection technique based on clustering, is proposed and experiments show that LOGAN identifies bias in a local region and allows us to better analyze the biases in model predictions. Expand
...
1
2
...