Integrating Taxonomies 瞿裕忠(Yuzhong Qu) yzqu@nju.edu.cn
Outline Integrating catalogs Leaning to matching ontologies WWW2001 Leaning to matching ontologies VLDB2003 Merging ontologies JWS2006
Reference Agrawal R, Srikant R. On integrating catalogs. Proceedings of the 10th international conference on World Wide Web. ACM, 2001: 603-612. [157] Doan, A., Madhavan, J., Dhamankar, R., Domingos,P., and Halevy, A.Y. Learning to Match Ontologies on the Semantic Web. VLDB J. 12(4) (2003), 303-319 [467] Kotis K, Vouros G A, Stergiou K. Towards automatic merging of domain ontologies: The HCONE-merge approach. Web Semantics: Science, Services and Agents on the World Wide Web, 2006, 4(1): 60-79. [91]
Integrating Catalogs S1 Sm C1 Cn d1 d2
Naive Bayes Classification
Enhanced Algorithm Similarity information implicit in the source Documents in the same source category are more likely belong to the same target category (in the master catalog)
Enhanced Algorithm (ENB)
Enhanced Algorithm (ENB)
Analysis and Experiment The highest accuracy achievable with the enhanced technique can be no worse than what can be achieved with the standard Naive Bayes classification. Experiments indicate that the proposed technique can result in large accuracy improvements.
Learning to match ontologies
The GLUE architecture
Joint probability distribution
Estimating the joint distribution of concepts
The Learners The Content Learner The Name Learner The Meta-Learner
Domain-Independent Constraints Neighborhood Two nodes match if their children also match. Two nodes match if their parents match and at least x% of their children also match. Two nodes match if their parents match and some of their descendants also match. Union If all children of node X match node Y, then X also matches Y.
Relaxation labeling
Experiments Removed all nodes with fewer than 5 instances On average only 30 to 90 data instances per leaf node
Matching accuracy of GLUE Intermediate approaches: firstly convert one data model to the other, and then reuse certain schema matching or ontology matching methods to discover simple mappings
Ontology merging problem Mapping them to an intermediate ontology. Get the minimal union of their (translated) vocabularies and axioms with respect to their alignment.
S-morphism and the intermediate ontology Semantic homomorphism (preserving partial order)
Entity category and taxonomy
More reference Zhang D, Lee W S. Web taxonomy integration using support vector machines. Proceedings of the 13th international conference on World Wide Web. ACM, 2004:472-481. [60] Flouris G, Manakanatas D, Kondylakis H, et al. Ontology change: Classification and survey. The Knowledge Engineering Review, 2008, 23(2): 117-152. [189]
致谢 http://ws.nju.edu.cn