Publications
Quantifying bias in face verification system
Summary
Summary
Machine learning models perform face verification (FV) for a variety of highly consequential applications, such as biometric authentication, face identification, and surveillance. Many state-of-the-art FV systems suffer from unequal performance across demographic groups, which is commonly overlooked by evaluation measures that do not assess population-specific performance. Deployed systems with bias...
Tools and practices for responsible AI engineering
Summary
Summary
Responsible Artificial Intelligence (AI)—the practice of developing, evaluating, and maintaining accurate AI systems that also exhibit essential properties such as robustness and explainability—represents a multifaceted challenge that often stretches standard machine learning tooling, frameworks, and testing methods beyond their limits. In this paper, we present two new software libraries—hydra-zen and...
A reverse approach to named entity extraction and linking in microposts
Summary
Summary
In this paper, we present a pipeline for named entity extraction and linking that is designed specifically for noisy, grammatically inconsistent domains where traditional named entity techniques perform poorly. Our approach leverages a large knowledge base to improve entity recognition, while maintaining the use of traditional NER to identify mentions...