CFB Lecture Series: “Digital Intuition: Understanding Money with Common Sense”

ABSTRACT: When we communicate, we rely on a large body of shared assumptions about the world that we use to understand each other. We use this intuition everywhere: when we go into a cafe, we know we can buy coffee there; we know our computer mouse won’t chomp on our fingers; and we know not to tell people that when you drop something it will fall down. When we interact with a computer or device, or when we look at large quantities of unstructured knowledge using a computer, we become frustrated because these devices clearly lack the intuitions that we expect from the intelligent creatures that inhabit our world.

We would like to capture some of this digital intuition using common sense knowledge and show how we can use such intuition to help people, businesses, and communities understand and spend their money better. In fact, many barriers we face today in artificial intelligence are due to the fact that computers do not share our basic knowledge about the world. We present a way of using the new technique of Blending to infuse any data set with common sense. When domain-specific data is combined with the general knowledge in Open Mind Common Sense (OMCS), new ways of organizing, visualizing, and reasoning over the data emerge. In domains such as consumer lifestyle modeling, knowledge acquisition from free text, and personal financial management, most information based on natural language can benefit from a little added common sense.

WHEN: Thursday, March 12th at 1pm

WHERE: Wiesner Room, MIT Media Lab (2nd Floor)

BIOGRAPHY: Catherine Havasi has been active in common sense research since 1999. She is one of the co-founders of the Open Mind Common Sense project at the MIT Media Lab, and one of the current authors of the of the common sense resource ConceptNet and reasoning technique AnalogySpace. She has chaired a series of workshops on common sense reasoning and its applications to various domains at the last three intelligent user interfaces conferences. She received both her BS and MS in computer science from MIT. This is her last year as a PhD student at Brandeis University under James Pustejovsky.