Knowledge Augmentation for Aligning Ontologies: An Evaluation in the Biomedical Domain

Authors: 
Zhang, S.; Bodenreider, O.
Author: 
Zhang, S
Bodenreider, O
Year: 
2003
Venue: 
Proceedings of the Semantic Integration Workshop, 2003
URL: 
http://mor.nlm.nih.gov/pubs/pdf/2003-iswc-semint-sz.pdf
Citations: 
5
Citations range: 
1 - 9
AttachmentSize
Zhang2003KnowledgeAugmentationfor.pdf60.05 KB

The objective of this study is to evaluate the contribution to semantic integration of the semantic relations extracted from concept names, representing augmented knowledge. Three augmentation methods – based on linguistic phenomena – are investigated (reification, nominal modification, and prepositional attachment). The number of concepts aligned in two ontologies of anatomy before and after augmentation serves as the evaluation criterion. Among the 2353 concepts exhibiting lexical resemblance across systems, the number of concepts supported by structural evidence (i.e., shared
hierarchical relations) increased from 71% before augmentation to 87% after augmentation. The relative contribution of each augmentation method to the alignment is presented. The limitations of this study and the generalization of augmentation methods are discussed.