I am a broadly interdisciplinary artificial intelligence researcher specializing in natural language processing.
A central focus of my research is on how we can teach computers question answering in the form of passing standardized science exams, as written, using a combination of scientific knowledge and common-sense reasoning skills. In particular, I focus on methods of automated inference that generate explanations for why the answer is correct. The Explanation Bank contains many such resources for explanation-centered inference, including WorldTree and EntailmentBank, that help power some of the highest-performing language models available, including the Allen Institute for Artificial Intelligence’s GPT3 competitor, MACAW.
I also explore how we can use text-based video games as a vehicle for studying scientific and common-sense reasoning, particularly by creating new virtual environments to encourage and measure these capacities for reasoning.
I uniquely have two distinct educational backgrounds, one in natural language processing, cognition, and computer science, the other in physics, electrical engineering, and sensing. I maintain active outreach in grounding science education through sensing, largely in the form of open source hardware like the tricorder project, and projects like the open source computed tomography scanner. This work has been widely featured in over 50 international news media articles, including Reuters, Forbes, WIRED, MSNBC, and the Washington Post, as well as an invited talk at TEDxBrussels 2012. In 2015, my open source science tricorder was honoured by being placed on permanent exhibit at the German Museum of Technology in Berlin.
Assistant Professor, School of Information, University of Arizona
office: harvill 437C