My research interests are in human-centered natural language processing.
Specifically, I'm interested in the implicit knowledge that NLP models acquire during training (both supervised and unsupervised), and how to extract this knowledge and present it to human stakeholders in ways that let them make more effective and ethical use of those models. I do both algorithmic work, coming up with methods to effectively extract knowledge from models, and human-subject experimentation work to better understand how humans work with those models.
