Growing Ontologies (1998)
http://www-eksl.cs.umass.edu/papers/98-20.pdf
http://eksl-www.cs.umass.edu/papers/cohen-tr98-20.
http://eksl-www.cs.umass.edu/papers/cohen-aaai.pdf
CACHED:
|
Popular Tags
No tags have been applied to this document.
BibTeX | Add To MetaCart
author = {Paul R. Cohen},
title = {Growing Ontologies},
year = {1998}
}
Bookmarks
OpenURL
Abstract:
Conceptual structures or ontologies are usually built by hand by skilled knowledge engineers. This paper presents a theory of how conceptual structure may be acquired by an intelligent agent interacting with its environment in an unsupervised way. Categories of activities are learned, then abstractions over these categories result in concepts. The entire conceptual structure is based on activities. The meanings of concepts and of conceptualizations of activities are discussed. Systems that implement aspects of the theory are presented, and their general characteristics described. 3 Introduction The subject of this paper is the foundation of conceptual systems. In artificial intelligence, conceptual systems are sometimes called ontologies and they are usually built by highly-trained knowledge engineers. It's less clear how humans acquire conceptual systems, or rather, the scope of the innate endowment is unclear. In any case, if machines could acquire conceptual knowledge with the s...
Citations
| 216 | Family resemblances: Studies in the internal structure of categories – Mervis - 1975 |
| 110 | The body in the mind – Johnson |
| 80 | On the thresholds of knowledge – Lenat, Feigenbaum - 1991 |
| 67 | How to build a baby: II. Conceptual primitives – Mandler - 1992 |
| 52 | Language as a dynamical system – Elman - 1995 |
| 46 | Made-up minds – Drescher - 1991 |
| 31 | A control basis for learning multifingered grasps – Coelho, Grupen - 1997 |
| 16 | The epigenesis of mind: Essays on biology and cognition. Hillsdale NJ: Erlbaum – Carey, Gelman - 1991 |
| 5 | do infants learn about the physical world – How - 1994 |
