A Computational Theory of Vocabulary Expansion

As part of an interdisciplinary project to develop a compu-tational cognitive model of a reader of narrative text, we aredeveloping a computational theory of how natural-language-understanding systems can automatically expand their vocab-ulary by determining from context the meaning of words thatare unknown, misunderstood, or used in a new sense. ‘Con-text’ includes surrounding text, grammatical information, andbackground knowledge, but no external sources. Our thesisis that the meaning of such a word can be determined fromcontext, can be revised upon further encounters with the word,“converges” to a dictionary-like definition if enough contexthas been provided and there have been enough exposures tothe word, and eventually “settles down” to a “steady state”that is always subject to revision upon further encounters withthe word. The system is being implemented in the SNePSknowledge-representation and reasoning system.This document is a slightly modified version (containing thealgorithms that appear in Figure 1, below) of that which isto appear in Proceedings of the 19th Annual Conference ofthe Cognitive Science Society (Stanford University) (Mahwah,NJ: Lawrence Erlbaum Associates). It is Technical Report97-08(Buffalo: SUNY Buffalo Department of Computer Sci-ence) and Technical Report 97-2(Buffalo: SUNY BuffaloCenter for Cognitive Science). It is also available on-lineat .

[1]  R. Sternberg Most vocabulary is learned from context. , 1987 .

[2]  Gary G. Hendrix,et al.  LEARNING BY BEING TOLD: ACQUIRING KNOWLEDGE FOR INFORMATION MANAGEMENT , 1983 .

[3]  Robert C. Berwick,et al.  Learning Word Meanings From Examples , 1983, IJCAI.

[4]  M. Ross Quillian,et al.  The teachable language comprehender: a simulation program and theory of language , 1969, CACM.

[5]  P. Johnson-Laird The mental representation of the meaning of words , 1987, Cognition.

[6]  Rohini K. Srihari Extracting visual information from text: using captions to label faces in newspaper photographs , 1992 .

[7]  L. Gleitman The Structural Sources of Verb Meanings , 2020, Sentence First, Arguments Afterward.

[8]  Stuart C. Shapiro,et al.  A Model for Belief Revision , 1988, Artif. Intell..

[9]  Rohini K. Srihari,et al.  Piction: A System That Uses Captions to Label Human Faces in Newspaper Photographs , 1991, AAAI.

[10]  Stuart C. Shapiro,et al.  Models and Minds: Knowledge Representation for Natural-Language Compe-tence , 1991 .

[11]  W. Rapaport,et al.  The SNePS family , 1992 .

[12]  H. Chertkow,et al.  Semantic memory , 2002, Current neurology and neuroscience reports.

[13]  Stuart C. Shapiro,et al.  The CASSIE Projects: An Approach to Natural Language Competence , 1989, EPIA.

[14]  Stuart C. Shapiro,et al.  THE SNePS SEMANTIC NETWORK PROCESSING SYSTEM , 1979 .

[15]  Maria R. Cravo,et al.  How to change your mind , 1991 .

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

[17]  Steven L. Lytinen,et al.  The Ups and Downs of Lexical Acquisition , 1994, AAAI.

[18]  A. Cremers Deixis in narrative : a cognitive science perspective , 1996 .

[19]  Wlodek Zadrozny,et al.  Semantics of Paragraphs , 1991, Comput. Linguistics.

[20]  Stuart C. Shapiro,et al.  Title Index , 1986, CL.

[21]  João P. Martins,et al.  SNePSwD: A newcomer to the SNePS family , 1993, J. Exp. Theor. Artif. Intell..

[22]  Dave Tyson How to change , 2007 .

[23]  David M. Keirsey Word Learning With Hierarchy-Guided Inference , 1982, AAAI.

[24]  J. Siskind A computational study of cross-situational techniques for learning word-to-meaning mappings , 1996, Cognition.

[25]  Peter M. Hastings Automatic acquisition of word meaning from context , 1994 .

[26]  Karen Ehrlich Automatic vocabulary expansion through narrative context , 1995 .

[27]  S. T. Buckland,et al.  An Introduction to the Bootstrap. , 1994 .

[28]  William J. Rapaport,et al.  Syntactic Semantics: Foundations of Computational Natural-Language Understanding , 1988 .

[29]  Michael G. Dyer,et al.  The Self-Extending Phrasal Lexicon , 1987, Comput. Linguistics.