Semantic translation
This article needs additional citations for verification. (December 2009) |
Semantic translation is the process of using
An example of semantic translation is the conversion of
Semantic translation should be differentiated from data mapping tools that do simple one-to-one translation of data from one system to another without actually associating meaning with each data element.
Semantic translation requires that data elements in the source and destination systems have "semantic mappings" to a central registry or registries of data elements. The simplest mapping is of course where there is equivalence. There are three types of
- ClassEquivalence - indicating that class or "concepts" are equivalent. For example: "Person" is the same as "Individual"
- Property Equivalence - indicating that two properties are equivalent. For example: "PersonGivenName" is the same as "FirstName"
- Instance Equivalence - indicating that two individual instances of objects are equivalent. For example: "Dan Smith" is the same person as "Daniel Smith"
Semantic translation is very difficult if the terms in a particular data model do not have direct one-to-one mappings to data elements in a foreign data model. In that situation, an alternative approach must be used to find mappings from the original data to the foreign data elements. This problem can be alleviated by centralized metadata registries that use the ISO-11179 standards such as the
See also
- Data mapping
- Federated search
- Intelligent agents
- ISO/IEC 11179
- National Information Exchange Model
- Semantic heterogeneity
- Semantic mapper
- Semantic Web
- Vocabulary-based transformation
- Web Ontology Language
References
- ISBN 978-94-017-1769-4.