Use this URL to cite or link to this record in EThOS: http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.573577
Title: Semantic matching for the medical domain
Author: Shamdasani, Jetendr
Awarding Body: University of the West of England, Bristol
Current Institution: University of the West of England, Bristol
Date of Award: 2011
Availability of Full Text:
Access from EThOS:
Abstract:
In recent years an effort has been made to find ways of representing data in a more organised and linked manner that is better suited for use by com- puter systems. Ontologies have been considered as a potential means of representing information in a structured way. This is achieved through the introduction of a top level semantic layer for data descriptions. Although ontologies have been seen a possible solution to the problem of data hetero- geneity, there now exists a problem of heterogeneity between ontologies. One approach that has been put forward to address some of the chal- lenges of semantic heterogeneity between ontologies is known as ontology alignment. The majority of the ontology alignment approaches today de- tect a single relationship between ontology features, namely equivalence. In this thesis an algorithm is presented which is able to discover subsumption as well as equivalence relationships between concepts in two ontologies. This thesis presents a domain specific solution to the problem of semantic matching by modifying the SMatch algorithm to function in the medical do- main. The SMatch approach uses a single source of background knowledge, the WordNet thesaurus. Using a general resource as a source of background knowledge is not always idealy suited to the problem of semantic matching in the domain of medicine. This work removes the reliance of the SMatch algorithm on WordNet to make it applicable to the specific terminology of the medical domain. This is done by using the UMLS metathesaurus.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID: uk.bl.ethos.573577  DOI: Not available
Share: