Script Recognition with Hierarchical Feature Maps

The hierarchical feature map system recognizes an input story as an instance of a particular script by classifying it at three levels: scripts, tracks and role bindings. The recognition taxonomy, i.e. the breakdown of each script into the tracks and roles, is extracted automatically and independently for each script from examples of script instantiations in an unsupervised self-organizing process. The process resembles human learning in that the differentiation of the most frequently encountered scripts become gradually the most detailed. The resulting structure is a hierarchical pyramid of feature maps. The hierarchy visualizes the taxonomy and the maps lay out the topology of each level. The number of input lines and the self-organization time are considerably reduced compared to the ordinary single-level feature mapping. The system can recognize incomplete stories and recover the missing events. The taxonomy also serves as memory organization for script-based episodic memory. The maps assign a unique memory location for each script instantiation. The most salient parts of the input data are separated and most resources are concentrated on representing them accurately.

[1]  Janet L. Kolodner,et al.  Maintaining Organization in a Dynamic Long-Term Memory , 1983, Cogn. Sci..

[2]  James L. McClelland,et al.  Mechanisms of Sentence Processing: Assigning Roles to Constituents of Sentences , 1986 .

[3]  John B. Black,et al.  Scripts in memory for text , 1979, Cognitive Psychology.

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

[5]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[6]  R. Miikkulainen,et al.  A modular neural network architecture for sequential paraphrasing of script-based stories , 1989, International 1989 Joint Conference on Neural Networks.

[7]  Noel E. Sharkey,et al.  What is the point of integration? The loci of knowledge-based facilitation in sentence processing , 1987 .

[8]  Arthur C. Graesser,et al.  Recognition memory for typical and atypical actions in scripted activities: Tests of a script pointer + tag hypothesis , 1979 .

[9]  Richard Edward Cullingford,et al.  Script application: computer understanding of newspaper stories. , 1977 .

[10]  Noel E. Sharkey,et al.  Word Recognition in a Functional Context: The Use of Scripts in Reading. , 1985 .

[11]  T. Kohonen.  Self-organized formation of topographically correct feature maps , 1982 .

[12]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[13]  Janet L. Kolodner,et al.  Reconstructive Memory: A Computer Model , 1983, Cogn. Sci..

[14]  Roger C. Schank,et al.  Scripts, plans, goals and understanding: an inquiry into human knowledge structures , 1978 .

[15]  Noel E. Sharkey,et al.  Mixing Binary and Continuous Connection Schemes for Knowledge Access , 1986, AAAI.

[16]  Ii Gerald Francis Dejong.  Skimming stories in real time: an experiment in integrated understanding. , 1979 .