Script-based inference and memory retrieval in subsymbolic story processing

DISCERN is an integrated natural language processing system built entirely from distributed neural networks. It reads short narratives about stereotypical event sequences, stores them in episodic memory, generates fully expanded paraphrases of the narratives, and answers questions about them. Processing in DISCERN is based on hierarchically-organized backpropagation modules, communicating through a central lexicon of word representations. The lexicon is a double feature map system that transforms each orthographic word symbol into its semantic representation and vice versa. The episodic memory is a hierarchy of feature maps, where memories are stored “one-shot” at different locations. Several high-level phenomena emerge automatically from the special properties of distributed neural networks in this model. DISCERN learns to infer unmentioned events and unspecified role fillers, generates expectations and defaults, and exhibits plausible lexical access errors and memory interference behavior. Word semantics, memory organization, and appropriate script inferences are automatically extracted from examples. DISCERN shows that high-level natural language processing is feasible through integrated subsymbolic systems. Subsymbolic control of high-level behavior and representing and learning abstractions are the two main challenges in scaling up the approach to more open-ended tasks.

[1]  N. E. Sharkey,et al.  A PDP learning approach to natural language understanding , 1989 .

[2]  Lance A. Miller,et al.  Review of The process of question answering: a computer simulation of cognition by Wendy G. Lehnert. Lawrence Erlbaum Associates 1978. , 1980 .

[3]  David S. Touretzky Connectionism and Compositional Semantics , 1989 .

[4]  M. Mattson,et al.  From words to meaning: A semantic illusion , 1981 .

[5]  C. P. Dolan Tensor manipulation networks: connectionist and symbolic approaches to comprehension, learning, and planning , 1989 .

[6]  Geoffrey E. Hinton,et al.  Schemata and Sequential Thought Processes in PDP Models , 1986 .

[7]  Jordan B. Pollack,et al.  Recursive Distributed Representations , 1990, Artif. Intell..

[8]  A. Graesser,et al.  Memory for typical and atypical actions in scripted activities. , 1980 .

[9]  Risto Miikkulainen,et al.  Trace feature map: a model of episodic associative memory , 2004, Biological Cybernetics.

[10]  Michael G. Dyer,et al.  Propagation Filters in PDS Networks for Sequencing and Ambiguity Resolution , 1991, NIPS.

[11]  B. Underwood Interference and forgetting. , 1957, Psychological review.

[12]  Risto Miikkulainen,et al.  Script Recognition with Hierarchical Feature Maps , 1992 .

[13]  W. H. Sumby,et al.  Word frequency and serial position effects , 1963 .

[14]  Mark F. St. John,et al.  The Story Gestalt: A Model of Knowledge-Intensive Processes in Text Comprehension , 1992, Cogn. Sci..

[15]  Roberto Pieraccini,et al.  A Learning Approach to Natural Language Understanding , 1994, ArXiv.

[16]  E. Warrington,et al.  Cognitive Neuropsychology: A Clinical Introduction , 1990 .

[17]  Risto Miikkulainen,et al.  Subsymbolic natural language processing - an integrated model of scripts, lexicon, and memory , 1993, Neural network modeling and connectionism.

[18]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

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

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

[21]  J. Hall,et al.  Learning as a function of word-frequency. , 1954, The American journal of psychology.

[22]  Risto Mukkulainen,et al.  Script Recognition with Hierarchical Feature Maps , 1990 .

[23]  Michael G. Dyer,et al.  Storing and Generalizing Multiple Instances While Maintaining Knowledge-Level Parallelism , 1989, IJCAI.

[24]  Geoffrey E. Hinton Tensor Product Variable Binding and the Representation of Symbolic Structures in Connectionist Systems , 1991 .

[25]  Stevan Harnad,et al.  Symbol grounding problem , 1990, Scholarpedia.

[26]  Geoffrey E. Hinton Mapping Part-Whole Hierarchies into Connectionist Networks , 1990, Artif. Intell..

[27]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[28]  Charles J. Fillmore,et al.  THE CASE FOR CASE. , 1967 .

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

[30]  Michael G. Dyer,et al.  Argument representation for editorial text , 1990, Knowl. Based Syst..

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

[32]  John F. Reeves,et al.  Computational morality: a process model of belief conflict and resolution for story understanding , 1991 .

[33]  Geoffrey E. Hinton,et al.  A general framework for parallel distributed processing , 1986 .

[34]  Paul Smolensky,et al.  Tensor Product Variable Binding and the Representation of Symbolic Structures in Connectionist Systems , 1990, Artif. Intell..

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

[36]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[37]  Walter Anthony Cook Case Grammar Theory , 1979 .

[38]  M R Quillian,et al.  Word concepts: a theory and simulation of some basic semantic capabilities. , 1967, Behavioral science.

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

[40]  A. Caramazza Some aspects of language processing revealed through the analysis of acquired aphasia: the lexical system. , 1988, Annual review of neuroscience.

[41]  W. Kintsch,et al.  Memory and cognition , 1977 .

[42]  Risto Miikkulainen,et al.  Natural Language Processingwith Modular Neural Networks and Distributed Lexicon , 1991 .

[43]  Risto Miikkulainen,et al.  Natural Language Processing With Modular PDP Networks and Distributed Lexicon , 1991, Cogn. Sci..

[44]  Janet L. Kolodner,et al.  Retrieval and organizational strategies in conceptual memory: a computer model , 1980 .

[45]  Wendy Grace Lehnert,et al.  The Process of Question Answering , 2022 .

[46]  Michael Lebowitz,et al.  Generalization and memory in an integrated understanding system , 1980 .

[47]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[48]  Barbara Hayes-Roth,et al.  The use of schemata in the acquisition and transfer of knowledge , 1979, Cognitive Psychology.

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

[50]  A. Baddeley The psychology of memory , 1976 .