Beating Common Sense into Interactive Applications

TLDR

Artificial intelligence has long aimed to embed commonsense knowledge into computers to enable reasoning about everyday life, yet practical use in interactive applications is widely regarded as impractical until knowledge bases are complete and reasoning robust. This article surveys several intelligent interface agents that successfully employ commonsense knowledge and reflects on interface design principles that enable such use. The survey examines applications developed at MIT Media Lab that integrate commonsense knowledge despite its limited coverage and unreliable inference. These agents demonstrate that commonsense knowledge can be effectively applied in interactive settings, achieving success despite current system shortcomings.

Abstract

A long-standing dream of artificial intelligence has been to put commonsense knowledge into computers -- enabling machines to reason about everyday life. Some projects, such as Cyc, have begun to amass large collections of such knowledge. However, it is widely assumed that the use of common sense in interactive applications will remain impractical for years, until these collections can be considered sufficiently complete and commonsense reasoning sufficiently robust. Recently, at the Massachusetts Institute of Technology's Media Laboratory, we have had some success in applying commonsense knowledge in a number of intelligent interface agents, despite the admittedly spotty coverage and unreliable inference of today's commonsense knowledge systems. This article surveys several of these applications and reflects on interface design principles that enable successful use of commonsense knowledge.