Integrating knowledge sources in language comprehension

Multiple types of knowledge (syntax, semantics, pragmatics, etc.) contribute to establishing the meaning of an utterance. Immediate application of these knowledge sources is necessary to satisfy the real-time constraintof 200 to 300words per minute for adult comprehension, since delaying the use of a knowledge source introduces computational inefficiencies in the form of overgeneration. On the other hand, ensuring 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 present NLSoar, 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.

[1]  D. G. Hays.  Dependency Theory: A Formalism and Some Observations , 1964 .

[2]  Igor Mel’čuk,et al.  Dependency Syntax: Theory and Practice , 1987 .

[3]  W. Marslen-Wilson,et al.  The temporal structure of spoken language understanding , 1980, Cognition.

[4]  Lawrence Birnbaum,et al.  Problems in conceptual analysis of natural language , 1979 .

[5]  Allen Newell,et al.  Toward a Soar theory of taking instructions for immediate reasoning tasks , 1993 .

[6]  P. Johnson-Laird.  Mental models , 1989 .

[7]  Mark Steedman,et al.  Interaction with context during human sentence processing , 1988, Cognition.

[8]  Richard L. Lewis,et al.  Toward a unified theory of immediate reasoning in Soar , 1993 .

[9]  Richard L. Lewis,et al.  Soar as a unified theory of cognition: spring 1990 , 1993 .

[10]  Michael Hucka,et al.  Robo-Soar: An integration of external interaction, planning, and learning using Soar , 1991, Robotics Auton. Syst..

[11]  K. Rayner,et al.  Making and correcting errors during sentence comprehension: Eye movements in the analysis of structurally ambiguous sentences , 1982, Cognitive Psychology.

[12]  A. Newell.  Unified Theories of Cognition , 1990 .

[13]  Marcel Adam Just,et al.  A Model of the Time Course and Content of Reading , 1982, Cogn. Sci..

[14]  R. Schank,et al.  Inside Computer Understanding , 1981 .

[15]  Victor R. Lesser,et al.  The Hearsay-II Speech-Understanding System: Integrating Knowledge to Resolve Uncertainty , 1980, CSUR.

[16]  Sandiway Fong,et al.  The Computational Implementation of Principle-Based Parsers , 1989, IWPT.

[17]  James F. Allen.  Natural language understanding , 1987, Bejnamin/Cummings series in computer science.

[18]  N. Curteanu.  Book Reviews: Lecture on Contemporary Syntactic Theories: An Introduction to Unification-Based Approaches to Grammar , 1987, CL.

[19]  C. Pollard,et al.  Center for the Study of Language and Information , 2022 .

[20]  Allen Newell,et al.  SOAR: An Architecture for General Intelligence , 1987, Artif. Intell..

[21]  Naomi Sager,et al.  Natural language information processing , 1980 .

[22]  CurteanuNeculai.  Review of "Lecture on contemporary syntactic theories , 1987 .

[23]  John C. Reynolds,et al.  School of Computer Science , 1992 .

[24]  Bradley L. Pritchett.  Garden Path Phenomena and the Grammatical Basis of Language Processing , 1988 .