Information Technology Reference
In-Depth Information
A formal definition of ontology is proposed in Gruber (1993) according to whom “an ontology is
an explicit specification of a conceptualization;” conceptualization is referred to as an abstract model
of a specified domain in which the component concepts are identified; explicit means that the type of
concepts used and the constraints on them are well defined; formal is referred to as the ontology pro-
priety of being “machine-readable”, shared is about the propriety that an ontology captures consensual
knowledge, accepted by a group of person, not only by individuals.
We also consider other definitions of ontology; in Neches et al., (1991) “an ontology defines the basic
terms and relations comprising the vocabulary of a topic area, as well as the rules for combining terms
and relations to define extensions to the vocabulary.” This definition indicates the way to proceed in
order to build an ontology: (i) identification of the basic terms and their relations; (ii) agreeing on the
rules that arrange them; (iii) definition of terms and relations among concepts.
From this perspective, an ontology does not include just the terms that explicitly are defined in it, but
also those that can be derived by means of well defined rules and properties. In our work, the ontology
can be seen as the set of “terms” and “relations” among them, denoting the concepts that are used in a
domain. We use ontologies to represent the user interest domain.
Semantic r elatedness
The concept of “Semantic relatedness” refers to the perceived relations between words and concepts.
Several metrics have been defined in the literature in order to measure the Semantic relatedness of two
words.
These metrics can be grouped in the following categories:
Dictionary-based: Dictionaries are a natural linguistic information source for people knowledge
about the world; they form a knowledge base in which the headwords are defined by other head-
words and/or their derivatives;
Thesaurus-based: These metrics use a thesaurus in which words are related to concepts; each
word is related to a category by means of an index structure;
Semantic network-based: These metrics use Semantic networks, i.e. graphs in which the nodes
are the concepts and the arcs represent relations between concepts;
Integrated approach: This approach takes into account additional knowledge sources to enrich
the information already present in the network.
An exhaustive overview of the metrics based on these approaches can be found in Budanitsky (1999)
and a new approach for measuring Semantic similarity is proposed in Li, Bandar & Mclean (2003).
syste M architecture
We propose a Web search engine that takes into account relevance feedback to improve the precision
of an information retrieval system based on general ontologies. The information used to build the
domain ontology is dynamically extracted from WordNet (Miller, 1995). For this reason the query
structure is constituted as a list of terms to retrieve (i.e., subject keywords) and a domain of interest
(i.e., domain keyword) provided by the user using the system interface. For example, if a user wants
Search WWH ::




Custom Search