National Conference on Artificial Intelligence · 1992 · 14 citations · 12 references
ComputingVisualizationKnowledge RepresentationNatural Language ProcessingReading ComprehensionAnalogical ReasoningCausal Graphical ModelsEvent RepresentationEvent SemanticsMeaning RepresentationSystem RepresentationCausal RelationsCausal RepresentationCause RepresentationEvent Structure RepresentationEvent UnderstandingInternal Model FormationRepresentational ReasoningTransformations
This paper introduces the causal reconstruction task the task of reading a causal description of a physical system, forming an internal model of the specified behavior, and answering questions demonstrating comprehension and reasoning on the basis of the input description. A representation called transition space is introduced, in which events are depicted as path fragments in a space of transitions, or complexes of changes in the attributes of participating objects. By identifying partial matches between the transition space representations of events, a program called PATHFINDER is able to perform causal reconstruction on short causal descriptions presented in simplified English. Simple transformations applied to event representations prior to matching enable the program to bridge discontinuities arising from the writer's use of analogy or abstraction. The operation of PATHFINDER is illustrated in the context of a simple causal description extracted from the Encyclopedia Americana, involving exposure of film in a camera.
12
Kenneth D. Forbus · Artificial Intelligence · 1984 · 2K citations
A qualitative physics based on confluences
Johan de Kleer, John Seely Brown · Artificial Intelligence · 1984 · 1.5K citations
Benjamin Kuipers · Artificial Intelligence · 1986 · 1.4K citations
A Theory of Inferred Causation.
Judea Pearl, Thomas Verma · 1991 · 526 citations
The teachable language comprehender
M. Ross Quillian · Communications of the ACM · 1969 · 487 citations · Full text