CHAPTER 5 Representing Knowledge in Taxonomies and Ontologies

Learning from data is at the heart of cognitive computing. If a system cannot use data to improve its own performance without reprogramming, it isn’t considered to be a cognitive system. But to do that, there must be a wealth of data available at the heart of the environment, formats for representing the knowledge contained within that data, and a process for assimilating new knowledge. This is analogous to the way a child learns about the world through observation, experience, and perhaps instruction. This chapter looks at some simple knowledge representations before exploring more sophisticated and comprehensive approaches to knowledge representation: taxonomies and ontologies.

Representing Knowledge

In computer systems as in humans, knowledge may include facts or beliefs and general information. It should also include standard knowledge organizational structures such as ontologies and taxonomies—as well as relationships, rules, or properties that describe objects (nouns) and help to categorize them. For example, we may know that people are animals and Bob is a person, so Bob should have all the properties that we associate with animals. In people, we sometimes equate knowledge with understanding, but that’s not the case with computers. Of course, in a computer, it is possible to “know” a lot without “understanding” anything. In fact, that’s the basic definition of a database: a collection of associated data ...

Get Cognitive Computing and Big Data Analytics now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.