Natural language comprehension in Soar : spring 1991

Abstract: "Multiple types of knowledge (syntax, semantics, pragmatics, etc.) contribute to establishing the meaning of an utterance. Delaying the use of a knowledge source during language processing introduces computational inefficiencies in the form of overgeneration, making it difficult to satisfy the real-time constraint of 200 to 300 words per minute for adult comprehension. On the other hand, insuring that all relevant knowledge is brought to bear as each word in the sentence is understood is a difficult design problem. As a solution to this problem, we describe in detail the current version of NL-Soar, a language comprehension system that integrates disparate knowledge sources automatically.Through experience, the nature of the understanding process changes from deliberate, sequential problem solving to recognitional comprehension that applies all the relevant knowledge sources simultaneously to each word. The dynamic character of the system results directly from its implementation within the Soar architecture."