Ontology Learning Using Corpus-Derived Formal Contexts
Ontologies can be defined as logical theories describing some aspect of reality. Typically, such logical theories describe a specific domain, i.e., some part of reality within a certain field, topic, area, branch, situation, etc. For example, we could define an ontology for the domain of university organizations (compare the SWRC ontology described in [Sure et al., 2005]). We could also formalize the aspects of reality in the domains of medicine [Grenon et al., 2004] or biochemistry [The Gene Ontology Consortium, 2000]. Ontologies, as they are declarative in nature (they represent a logical theory) can be used for many applications in which a description of the domain is useful, for example, for inferring knowledge which is implicit in the current state of an information system, for integrating different data sources, etc. Popular definitions of ontologies in computer science are the following ones:
• “An ontology is an explicit specification of a conceptualization” (Gruber [Gruber, 1993]),
• “Ontology is the term used to refer to the shared understanding of some domain of interest [...] An ontology necessarily entails or embodies some sort of world view with respect to a given domain. The world view is often conceived as a set of concepts (e.g., entities, attributes, processes), their definitions and their interrelationships; this is referred to as conceptualization.” (Uschold and Grüninger [Uschold and Grüninger, 1996]),
• “An ontology is a formal, explicit specification of a shared conceptualization.” (Studer et al. [Studer et al., 1998]).