Dustin Arthur Smith

Learn More
In our research on Commonsense reasoning, we have found that an especially important kind of knowledge is knowledge about human goals. Especially when applying Com-monsense reasoning to interface agents, we need to recognize goals from user actions (plan recognition), and generate sequences of actions that implement goals (planning). We also often need to(More)
A metareasoning problem involves three parts: 1) a set of concrete problem domains; 2) reasoners to reason about the problems; and, 3) metareasoners to reason about the reason-ers. We believe that the metareasoning community would benefit from agreeing on the first two problems. To support this kind of collaboration, we offer an open source 3D sim-ulator(More)
We present a game-based interface for acquiring common sense knowledge. In addition to being interactive and entertaining, our interface guides the knowledge acquisition process to learn about the most salient characteristics of a particular concept. We use statistical classification methods to discover the most informative characteristics in the Open Mind(More)
Planning-based approaches to reference provide a uniform treatment of linguistic decisions, from content selection to lexical choice. In this paper, we show how the issues of lexical ambiguity, vague-ness, unspecific descriptions, ellipsis, and the interaction of subsective modifiers can be expressed using a belief-state planner modified to support(More)
Personal event management involves planning when, where and how events should occur, making sure the event's prerequisites are satisfied, and developing contingencies for when things go wrong. Conventional calendar and project management tools, however, only record and visualize explicit human decisions regarding event specifics. We present Event Minder, a(More)
Referring expressions such as " a long meeting " and " a restaurant near my brother's " depend on information from the context to be accurately resolved. Interpreting these expressions requires pragmatic inferences that go beyond what the speaker said to what she meant; and to do this one must consider the speaker's decisions with respect to her initial(More)
Referring expressions with vague and ambiguous modifiers, such as " a quick visit " and " the big meeting, " are difficult for computers to interpret because their words' meanings are in part defined by context, which changes throughout the course of an interpretation. In this paper, we present an approach to interpreting context-dependent referring(More)
When a person determines what he will say and how he will say it, he relies upon beliefs that he predicts to be shared with his audience. The difficulty of this inference task is amplified when a person speaks to a computer, because it is unclear what the computer knows and how the computer will use its knowledge to interpret the speaker's utterance. This(More)