Understanding Novel Language.

Abstract In this article we treat in some detail the problem of designing mechanisms that will allow us to deal with two types of novel language: (1) text requiring scheme learning; and (2) the understanding of novel metaphorical use of verbs. Schema learning is addressed by four types of processes: schema composition, secondary effect elevation, schema alteration, and volitionalization. The processing of novel metaphors depends on a decompositional analysis of verbs into “event shape diagrams,” along with a matching process that uses semantic marker-like information, to construct novel meaning structures. The examples we describe have been chosen to be types that occur commonly, so that rules that we need to understand them can also be used to understand a much wider range of novel language.

[1]  J. Fodor.  The Language of Thought , 1980 .

[2]  Richard Granger,et al.  FOUL-UP: A Program that Figures Out Meanings of Words from Context , 1977, IJCAI.

[3]  Kenneth D. Forbus.  Qualitative Process Theory , 1984, Artif. Intell..

[4]  Joseph Weizenbaum,et al.  Contextual understanding by computers , 1967, CACM.

[5]  Gerald DeJong.  Automatic Schema Acquisition in a Natural Language Environment , 1982, AAAI.

[6]  N. S. Sridharan,et al.  Plan Recognition Using A Hypothesize and Revise Paradigm , 1977, IJCAI.

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

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

[9]  Mallory Gordon Richard Selfridge,et al.  A process model of language acquisition , 1980 .

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

[11]  Chuck Rieger,et al.  The Commonsense Algorithm as a Basis for Comfuter Models of Human Memory, Inference, Belief and Contextual Language Comprehension , 1975, TINLAP.

[12]  David L. Waltz,et al.  A Knowledge-Based Approach to Language Processing : A Progress Report , 2002 .

[13]  Eugene Charniak.  Framed PAINTING: The Representation of a Common Sense Knowledge Fragment , 1977 .

[14]  Roger C. Schank,et al.  The Primitive ACTs of Conceptual Dependency , 1975, TINLAP.

[15]  Douglas B. Lenat,et al.  AM, an artificial intelligence approach to discovery in mathematics as heuristic search , 1976 .

[16]  Ray Jackendoff,et al.  A System of Semantic Primitives , 1975, TINLAP.

[17]  Scott E. Fahlman,et al.  NETL: A System for Representing and Using Real-World Knowledge , 1979, CL.

[18]  Daniel G. Bobrow,et al.  GUS, A Frame-Driven Dialog System , 1986, Artif. Intell..

[19]  Jon Doyle,et al.  Truth Maintenance Systems for Problem Solving , 1977, IJCAI.

[20]  C. Raymond Perrault,et al.  It's for Your Own Good: A Note on Inaccurate Reference. , 1981 .

[21]  Patrick Henry Winston,et al.  Learning structural descriptions from examples , 1970 .

[22]  Joseph Weizenbaum,et al.  and Machine , 1977 .

[23]  Wallace L. Chafe.  Some thoughts on schemata , 1975, TINLAP '75.

[24]  Timothy W. Finin.  The Semantic Interpretation of Nominal Compounds , 1980, AAAI.

[25]  Mark S. Fox,et al.  Knowledge Guided Learning of Structural Descriptions , 1977, IJCAI.

[26]  Richard Fikes,et al.  Learning and Executing Generalized Robot Plans , 1993, Artif. Intell..

[27]  Daniel G. Bobrow,et al.  SOME PRINCIPLES OF MEMORY SCHEMATA , 1975 .

[28]  Roger C. Schank,et al.  Language and Memory , 1986, Cogn. Sci..

[29]  Nick Cercone.  A Note on Representing Adjectives and Adverbs , 1977, IJCAI.

[30]  David L. Waltz,et al.  Event Shape Diagrams , 1982, AAAI.