Wentao Wang

I am a first-year PhD student at NYU Center for Data Science, working with Prof. Brenden Lake and Prof. Tal Linzen.

My research interests lie in the intersection of natural language processing, computational linguistics, and cognitive science. Specifically, I am interested in 1) interpretation of both human tasks (e.g., language processing) and black-box neural network models, 2) inducing structures from them, and 3) building models that can generalize robustly by combining them with structures and symbolic modules (through, e.g., neuro-symbolic methods). I believe compositionality is the key to both understanding and improving the generalization of models. I am also interested in interpretability of Transformers from both theoretical and empirical perspectives, and hope to connect it to linguistic/CogSci phenomena.