Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Background
First-year PhD student at NYU Center for Data Science
Research interests lie at the intersection of natural language processing, computational linguistics, and cognitive science
Focused on interpretability of human language processing tasks and black-box neural network models
Aims to induce structures from data and build robustly generalizing models by integrating structures and symbolic modules (e.g., via neuro-symbolic methods)
Believes compositionality is key to understanding and improving model generalization
Interested in theoretical and empirical interpretability of Transformers, with the goal of connecting it to linguistic and cognitive science phenomena