A Retrospective View of the Hearsay-II Architecture

The Hearsay model has heen presented as a paradigm for attacking errorful knowledge-intensive problems requiring multiple, cooperating knowledge sources. The Hearsay-II architecture is the latest attempt to explore the model. This paper describes experiences gained while successfully applying this architecture to the problem of speech understanding. The major conclusions are: 1. The paradigm of viewing problem solving in terms of hypothesize-and-test actions distributed among distinct representations of the problem has been shown to be computationally feasible. 2. A global working memory (the "blackboard"), in which the distinct representations are integrated in a uniform manner, has made it convenient to construct and integrate the individual sources of knowledge needed for the problem solution. 3. The use of a uniform data-directed structure for controlling knowledge-source activity has made the system easy to understand and modify. 4. A solution has been demonstrated to the problem of focus-of-attention in this type of control environment. This solution does not need to be modified when the sources of knowledge in the system are changed.

[1]  Carl Hewitt,et al.  Description and Theoretical Analysis (Using Schemata) of Planner: A Language for Proving Theorems and Manipulating Models in a Robot , 1972 .

[2]  Lee D. Erman,et al.  A model and a system for machine recognition of speech , 1973 .

[3]  Lee Daniel Erman,et al.  An environment and system for machine understanding of connected speech. , 1974 .

[4]  Marvin Minsky,et al.  A framework for representing knowledge , 1974 .

[5]  Victor R. Lesser,et al.  A Multi-Level Organization For Problem Solving Using Many, Diverse, Cooperating Sources Of Knowledge , 1975, IJCAI.

[6]  Richard D. Fennell,et al.  Parallelism in AI Problem Solving: A Case Study of Hearsay 2 , 1975 .

[7]  Gary G. Hendrix,et al.  Expanding the Utility of Semantic Networks Through Partitioning , 1975, IJCAI.

[8]  J M Tenenbaum,et al.  MSYS: A System for Reasoning About Scenes. , 1975 .

[9]  Victor Lesser,et al.  Organization of the Hearsay II speech understanding system , 1975 .

[10]  Lee D. Erman,et al.  The Hearsay-I Speech Understanding System: An Example of the Recognition Process , 1973, IEEE Transactions on Computers.

[11]  A. Smith,et al.  Word hypothesization in the hearsay II speech system , 1976, ICASSP.

[12]  Jack Mostow,et al.  Syntax and semantics in a distributed speech understanding system , 1976, ICASSP.

[13]  Azriel Rosenfeld,et al.  Scene Labeling by Relaxation Operations , 1976, IEEE Transactions on Systems, Man, and Cybernetics.

[14]  Victor Lesser,et al.  IN THE HEARSAY-II SPEECH UNDERSTANDING SYSTEM , 1976 .

[15]  Raj Reddy,et al.  The LOCUS Model of Search and its Use in Image Interpretation , 1977, IJCAI.

[16]  Robert S. Engelmore,et al.  A knowledge-based system for the interpretation of protein x-ray crystallographic data , 1977 .

[17]  Victor Lesser,et al.  Selection of word islands in the Hearsay-II speech understanding system , 1977 .

[18]  Mark S. Fox,et al.  Maximal Consistent Interpretations of Errorful Data in Hierarchically Modeled Domains , 1977, IJCAI.

[19]  Victor R. Lesser,et al.  Focus of Attention in the Hearsay-II Speech Understanding System , 1977, IJCAI.

[20]  Edward M. Riseman,et al.  Knowledge-directed learning , 1977, SGAR.

[21]  D. McKeown,et al.  Word verification in the Hearsay II speech understanding system , 1977 .

[22]  Gérard M. Baudet,et al.  Asynchronous Iterative Methods for Multiprocessors , 1978, JACM.