Epstein Secrets

y, there may be patterns across large numbers of nodes that merit encapsulation in individual nodes. For instance, if there are 1000 fairly similar ConceptNodes, it may be better not to merge them all together, but rather to create a single node to which they all link, reifying the category that they collect

tic knowledge programmed in. In the latter approach, one may use knowledge from statistical corpus analysis, one may use electronic resources like WordNet and FrameNet, and one may use sophisticated, specialized tools like natural language parsers with hand-coded grammars. Rather than trying to emulate

s of word sense creation. Suppose we have a WordNode W that has ReferenceLinks to a number of different Con- ceptNodes. A common case is that these ConceptNodes fall into clusters, each one denoting a "sense" of the word. The clusters are defined by the following relationships: 1. ConceptNodes within a clus

ords; a graph between word senses is drawn, and then solved as a Markov chain. In the original formulation, word senses are defined by appealing to WordNet, and affinity between word-senses is obtained via one of several similarity measures. Neither of these can be applied in learning a language de novo

ference problems, from the CogPrime perspective, is that assuming one provides the inference system with an appropriate set of perceptual and motor ConceptNodes and Schemallodes, the chains of inference involved are short. They involve about a dozen inferences, and this means that the search tree of possible

nature of human linguistic concepts is well known, and is illustrated in Figure 15.2 for the commonsense knowledge domain (using a graph drawn from WordNet, a huge con- cept hierarchy covering 50K+ English-language concepts), and in Figure 15.4 for a specialized knowledge subdomain, genetics. Due to thi

inference problems, from the CogPrime perspective, is that assuming one provides the inference system with an appropriate set of perceptual and motor ConceptNodes and SchemaNodes, the chains of inference involved are short. They involve about a dozen inferences, and this means that the search tree of possible P

l nature of human linguistic concepts is well known, and is illustrated in Figure 15.2 for the commonsense knowledge domain (using a graph drawn from WordNet, a huge con- cept hierarchy covering 50K+ English-language concepts), and in Figure 15.4 for a specialized knowledge subdomain, genetics. Due to this