Dissertation Talk: Learning from Language

Lecture: Dissertation Talk: CS | May 1 | 3-5 p.m. | 730 Sutardja Dai Hall

 Jacob Andreas, UC Berkeley

 Electrical Engineering and Computer Sciences (EECS)

Natural language is built from a library of concepts and compositional operators that provide a rich source of information about how humans understand the world. Can this information help us build better machine learning models? In this talk, we'll explore three ways of integrating compositional linguistic structure and learning: using language as a source of modular reasoning operators for question answering, as a scaffold for fast and generalizable reinforcement learning, and as a tool for understanding representations in neural networks.