Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Ontology Mapping Neural Network: An Approach to Learning and Inferring Correspondences Among Ontologies

Peng, Yefei (2010) Ontology Mapping Neural Network: An Approach to Learning and Inferring Correspondences Among Ontologies. Doctoral Dissertation, University of Pittsburgh. (Unpublished)

Primary Text

Download (5MB) | Preview


An ontology mapping neural network (OMNN) is proposed in order to learn and infer correspondences among ontologies. It extends the Identical Elements Neural Network (IENN)'sability to represent and map complex relationships. The learning dynamics of simultaneous (interlaced) training of similar tasks interact at the shared connections of the networks. The output of one network in response to a stimulus to another network can be interpreted as an analogical mapping. In a similar fashion, the networks can be explicitly trained to mapspecific items in one domain to specific items in another domain. Representation layer helpsthe network learn relationship mapping with direct training method.The OMNN approach is tested on family tree test cases. Node mapping, relationshipmapping, unequal structure mapping, and scalability test are performed. Results showthat OMNN is able to learn and infer correspondences in tree-like structures. Furthermore, OMNN is applied to several OAEI benchmark test cases to test its performance on ontologymapping. Results show that OMNN approach is competitive to the top performing systems that participated in OAEI 2009.


Social Networking:
Share |


Item Type: University of Pittsburgh ETD
Status: Unpublished
CreatorsEmailPitt UsernameORCID
Peng,, yefei_peng@yahoo.comYEP3
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Committee ChairMunro, Paulpmunro@mail.sis.pitt.eduPWM
Committee MemberParmanto, Bambangparmanto@pitt.eduPARMANTO
Committee MemberHe, Daqingdaqing@sis.pitt.eduDAH44
Committee MemberKarimi, Hassanhkarimi@sis.pitt.eduHKARIMI
Committee MemberSpring, Michaelspring@pitt.eduSPRING
Date: 12 May 2010
Date Type: Completion
Defense Date: 9 April 2010
Approval Date: 12 May 2010
Submission Date: 6 April 2010
Access Restriction: No restriction; Release the ETD for access worldwide immediately.
Institution: University of Pittsburgh
Schools and Programs: School of Information Sciences > Information Science
Degree: PhD - Doctor of Philosophy
Thesis Type: Doctoral Dissertation
Refereed: Yes
Uncontrolled Keywords: learning; ontology mapping; analogy; neural network
Other ID:, etd-04062010-184159
Date Deposited: 10 Nov 2011 19:34
Last Modified: 15 Nov 2016 13:38


Monthly Views for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item