1 / 9

Finding Implicit Relations in the Semantic Web

Finding Implicit Relations in the Semantic Web. Shridhar Bhalerao CMSC 601. Semantic Web. Is Web of Data . Each Data Resource is represented by a URI Data resources are linked to each other .The link also has a URI identifying it.

kaspar
Download Presentation

Finding Implicit Relations in the Semantic Web

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. Finding Implicit Relations in the Semantic Web ShridharBhalerao CMSC 601

  2. Semantic Web • Is Web of Data . • Each Data Resource is represented by a URI • Data resources are linked to each other .The link also has a URI identifying it. • Ontologies are used for conceptualizing , data is mapped to the concept. • Described Using RDF.

  3. Ontologies, RDF Triple, isparql • Conceptualization of data into classes. DBpedia Ontology . • Properties , Domain , Range. • RDF. • Example

  4. Querying the semantic web • Queries The queries are in the form of Rdf graph. • Isparql A tool for querying RDF datasets . User must know properties and classes of the ontology the dataset is using .

  5. Problem Statement • User query given in a single triple but the answer is present as n triples . • The relation is not present directly in the database. • The user creates the relation which he thinks is appropriate. works for Actor director

  6. Solution • Finding the N triple form of the user query . • Algorithm for finding destination class which scan all the properties in the ontology that have the domain of the 1st class .Create a triple with candidate class. • Tree form. • Output will give the links from the 1st class to destination class.

  7. Evaluation • Generate a set of queries having implicit relations from users . • Generate the correct triple from an ontology expert. Retrieve the answer set. • Find the correct triple using the algorithm. • Evaluate the result using precision and recall.

  8. Challenges • Presence of Multiple Paths. The two classes can be related by different relations . • Capturing the semantics of the relation given by the user and using it to find the correct path.

  9. Questions

More Related