Currently an Associate Research Scientist at the Data Science Institute and Adjunct Assistant Professor at Columbia Business School, Columbia University.
Research focuses on developing machine learning (ML) and natural language processing (NLP) techniques for social good, business, and healthcare.
Work includes building models for decision-making, financial analytics, predictive modeling, combating misinformation, and enhancing predictive healthcare.
Research spans probabilistic modeling, representation learning, Bayesian latent variable models of text, deep learning architectures, and natural language understanding.
Previously worked on multilingual information retrieval, machine translation for speech and text (including modeling comparable corpora), and speech recognition on low-resource platforms.