Ontology learning (ontology extraction, ontology generation, or ontology acquisition) is a subtask of information extraction. The goal of ontology learning is to semi-automatically extract relevant concepts and relations from a given corpus or other kinds of data sets to form an ontology.
The automatic creation of ontologies is a task that involves many disciplines. Typically, the process starts by extracting terms and concepts or noun phrase from plain text using a method from terminology extraction. This usually involves linguistic processors (e.g. part of speech tagging, phrase chunking). Then statistical or symbolic techniques are used to extract relation signatures. The intentional aspects of domain are formalized by Ontology. Extensional part is commanded by the knowledge based on instances of concepts and relations on the basis of ontology. For instance, these approaches try to detect that "to eat" denotes a relation between a concept denoted by "animal" and a concept denoted by "food". Recently, a graph-based approach has been proposed which extracts a domain taxonomy - i.e., the backbone of an ontology - from scratch.
Read more about Ontology Learning: See Also
Famous quotes containing the word learning:
“Learning without thinking is labor lost; thinking without learning is dangerous.”
—Chinese proverb.