I am a postdoc without a supervisor at New York University (NYU). My research is on interpretability and explainability for natural language processing, with the aim of understanding what it means for a deep neural network to be “interpreted by” or “explained to” a human audience. Interests include but are not limited to:
- BERTology and analysis of neural representations
- feature attribution, causality, and bias
- generative linguistics, syntax, and psycholinguistics
- theory of computation and formal languages
- theoretical foundations, rigor, and reproducibility
My collaborators at NYU include Tal Linzen and João Sedoc. I recently completed my PhD in Linguistics and Computer Science with Bob Frank and Dana Angluin at Yale University.
Education
- PhD, Yale University (2022)
- BA, University of Chicago (2015)
Professional Experience
- Assistant Professor/Faculty Fellow, New York University (2022–)
- Natural Language Machine Learning Intern, Apple (Summer 2021)
- Software Developer, Epic (2015–2016)
- Sales and Trading Intern, Wells Fargo Securities (Summer 2014)
