Implanting Rational Knowledge into Distributed Representation at Morpheme Level

Implicit knowledge and rational representation

It is commonplace in artificial intelligence to draw a distinction between the explicit knowledge appearing in an agent's memory and the implicit knowledge it represents. Many AI theories of knowledge assume this representation relation is logical, that is, that implicit knowledge is derived from explicit knowledge via a logic. Such theories, however, are limited in their ability to treat incom...

COPE: A Canonical Representation of Diagnosis Systems at Knowledge Level

This paper describes a way of recognizing equivalent knowledgebased diagnosis applications at knowledge level, based on the notion of Conceptual Equivalence, that is formally developed. This notion of Conceptual Equivalence induces the definition of a generic inference structure for knowledge-based diagnosis applications named COPE, acronym for Compare, Observe, Predict and Evaluate.

Bilingual Lexicon Extraction at the Morpheme Level Using Distributional Analysis

Bilingual lexicon extraction from comparable corpora is usually based on distributional methods when dealing with single word terms (SWT). These methods often treat SWT as single tokens without considering their compositional property. However, many SWT are compositional (composed of roots and affixes) and this information, if taken into account, can be very useful to match translational pairs,...

Knowledge Representation for Distributed System

The Shallow Level of Knowledge Representation

The premises of this paper are (a) that an intelligent machine's performance is inexorably tied to the representational form of its knowledge, and (b) that the computational parallel of humans' experience is the machine's input. Given this, our aim is to show that for a cognitive system to be able to demonstrate its intelligence eectively, then at least some of its knowledge must be in a repres...