60
Views
23
CrossRef citations to date
0
Altmetric
Original Articles

The Representation of Knowledge in Minds and Machines

Pages 411-420 | Published online: 21 Sep 2010
 

Abstract

Human knowledge can be represented as a propositional network in which the meaning of a node is defined by its position in the network. That is, the relationship between a node and its neighbours determines how this node is used in language understanding and production, i.e., its meaning. The propositions that make up such a network are predicate-argument structures with time and location slots. Schemas, frames, and production rules can be expressed in the same formalism. Implications for this contextual view of meaning are discussed. Since the construction of such a propositional network depends on hand coding and is therefore impractical, an alternative automatic statistical procedure is explored that yields a high-dimensional semantic space. Vectors in this space correspond to nodes in the propositional network, in that the meaning of a vector in the Latent Semantic Analysis space is given by its neighbouring vectors in that space. Les connaissances humaines peuvent etre representees sous la forme d'un reseau propositionnel dans lequel la signification d'un noeud est definie par sa position au sein du reseau. La relation entre un noeud et ses voisins determine la maniere dont ce noeud est utilise dans la comprehension et la production du langage, en d'autres termes, sa signification. Les propositions qui constituent un tel reseau sont des structures predicat-argument incluant une information temporelle et une information de localisation. Les schemas, les "frames" et les regles de production sont egalement exprimables a l'aide de ce formalisme. Les implications de cette interpretation contextuelle de la signification sont discutees dans le present article. Si la construction d'un tel reseau propositionnel dependait uniquement d'un codage manuel, elle serait de fait pratiquement irrealisable. C'est pourquoi une procedure statistique automatique est envisagee. Cette procedure produit un espace semantique a dimensions multiples. Les vecteurs dans cet espace correspondent aux noeuds du reseau propositionnel. Ainsi, la signification d'un vecteur dans l'espace de l'Analyse Semantique Latente est donnee par les vecteurs voisins au sein de cet espace.

Reprints and Corporate Permissions

Please note: Selecting permissions does not provide access to the full text of the article, please see our help page How do I view content?

To request a reprint or corporate permissions for this article, please click on the relevant link below:

Academic Permissions

Please note: Selecting permissions does not provide access to the full text of the article, please see our help page How do I view content?

Obtain permissions instantly via Rightslink by clicking on the button below:

If you are unable to obtain permissions via Rightslink, please complete and submit this Permissions form. For more information, please visit our Permissions help page.