I obtained my B.S degree in computer science and B.A. degree in mathematics from University of Minnesota. During that time, I was working with Dr. Daniel Kersten in computational vision and Linguist Hooi Ling Soh in linguistics research.
My research combines computer vision and natural language processing. I am particularly interested in the symbol grounding problem and my current work at VCLA is to develop statistical multi-modal models for grounding natural language semantics into visual images. My study explores both lexical embedding and semantic composition.