1 / 13

Discovering Ontological Semantics using FCA and SOM

Discovering Ontological Semantics using FCA and SOM. Advisor : Dr. Hsu Reporter : Wen-Hsiang Hu Author : Ching-Chieh Kiu and Chien-Sing Lee. M 2 USIC 2004. Outline. Motivation Objective Formal Concept Analysis (FCA) Ontology SOM Experiments Conclusion. Motivation.

ebazile
Télécharger la présentation

Discovering Ontological Semantics using FCA and SOM

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Discovering Ontological Semantics using FCA and SOM Advisor :Dr. Hsu Reporter:Wen-Hsiang Hu Author:Ching-Chieh Kiu and Chien-Sing Lee M2USIC 2004

  2. Outline • Motivation • Objective • Formal Concept Analysis (FCA) • Ontology • SOM • Experiments • Conclusion

  3. Motivation • Ontologies enable more intelligent interchange and reuse of data over the Internet. • However, not all applications use the same ontological model. Different sites have different contexts and different definitions for the concept. • This has caused the ontology interoperability problems to occur between sites.

  4. Objective • We use Formal Concept Analysis (FCA) and Self-Organizing Map (SOM) to discover and visualize the intrinsic relationship between ontological concepts.

  5. Formal Concept Analysis (1/2) • Formal Concept Analysis (FCA) is a conceptual clustering tool used for data analysis • In a formal concept k = (G, M, I) where G are objects, M are attributes and I is a binary relation between G and M. • The set of all formal concepts k is called concept lattice and is denoted by βk. objects relation attributes

  6. Formal Concept Analysis (2/2) • Concept lattice is the structured graph depicted according to the context (Figure 2).

  7. Ontology • Figure 1 illustrates the author and person concepts for the newspaper ontology obtained from Protégé.

  8. Self-Organizing Map • Visualization of the SOM can be represented using the U-matrix (unified distance matrix) method.

  9. Experiments (1/4) • Data • The ontology used in the experiment was a newspaper ontology obtained using Protégé. • matrix 26 * 72 • 26 concepts and 72 corresponding attributes were excerpted from the newspaper ontology using FCA

  10. Experiments (2/4) • FCA • All the concepts have the attributes of phone numbers and other information excluding the Author and News_Service concept. • Multiple inheritances of concepts can be easily viewed via the hierarchical structure of the concepts

  11. Experiments (3/4) • SOM • “Manager, Director, Columnist, Editor and Reporter” are grouped together to form a cluster and “Advertisement, Article, PersonalsAd and StandardAd” are grouped together to form another cluster.

  12. Experiments (4/4) • FCA • Advantages • The subconcept and superconcept relationships are clearly represented by the hierarchical structure. • Disadvantages • FCA is not viable to visualize the large ontology • SOM • Advantages • explain the concepts in the clusters are having the common attributes • Disadvantages • it is unable to visualize the inheritance relationship in between.

  13. Conclusion • We have presented the advantage of the FCA and SOM tools used for discovering and visualizing ontological semantics.

More Related