1 / 34

Traversing Documents by Using Semantic Relationships

Traversing Documents by Using Semantic Relationships. Presenter: Bilal Gonen. Semantic Browser. Semantic browser is a tool that supports browsing and navigation of a document space by utilizing the semantic relationships. Physical Links vs. Virtual Links. affects. co_occurs_with.

chacha
Télécharger la présentation

Traversing Documents by Using Semantic Relationships

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. Traversing Documents by Using Semantic Relationships Presenter: Bilal Gonen

  2. Semantic Browser • Semantic browser is a tool that supports browsing and navigation of a document space by utilizing the semantic relationships.

  3. Physical Links vs. Virtual Links affects co_occurs_with co_occurs_with href co_occurs_with href is_result_of co_occurs_with href is_result_of co_occurs_with affects analyzes is_result_of affects is_result_of href co_occurs_with is_result_of affects

  4. A Real Example How are these articles related? One common option is to use statistical techniques. How do we find other documents related with “melanoma”?

  5. Recommendation Systems Amazon, the best-known commercial recommender system, recommends books to customers based on the statistical similarity between customers' previous purchases. Customers who bought this item also often bought Statistical proximity The product: Digital Camera Digital Memory Card

  6. A Real Example Such a statistical technique may return these terms. There are no named relationships.

  7. Ontology Pathologic Function Ontology is at the heart of Semantic Web. rdfs:subClassOf Amino Acid Peptide or Protein Substance Disease or Syndrome affects rdfs:subClassOf rdfs:subClassOf Diagnostic Procedure Body Substance analyzes Neoplastic Process Schema level InstanceOf InstanceOf InstanceOf Instance level Kidney Neoplasms Ureteral Calculi

  8. Relationships In Ontology cancers breast cancer blood cancer bone cancer chromosomal disorder skin cancer non-melanoma euploidy melanoma aneuploidy monoploidy is_result_of

  9. A Real Example Our approach is to offer several relationships to the user. Name of files in which “aneuploidy” occurs. Return files which includes “aneuploidy” affects This is what user is interested in. co_occurs_with occurs_in is_result_of

  10. Java Script AJAX User Interface (HTML page) request user The advantage of the AJAX technology is to send and receive only needed information between the client and server. PubMed dataset JSP (Java Server Page) Lucene Index for documents Built in LSDIS Lab. This API is used to process the triples in the ontology. Because we also used the synonyms of the 21,945 MESH terms, therefore we used ~104,000 terms to index the documents. Lucene indexing is used to index the documents with the 21,945 MESH terms when they occur in the documents. Contains 48,252 documents Ontology SemDis API Contains 135 classes and 49 relationships in schema level. And 21,945 entity instances in the instance level

  11. AJAX (Asynchronous JavaScript And XML)

  12. AJAX (Asynchronous JavaScript And XML) Only this part is loaded to the client side.

  13. Java Script AJAX User Interface (HTML page) response request user The MESH term is sent to server as a request to get its types from the ontology by using the SemDis API. List of the documents are returned from the Lucene index. PubMed dataset JSP (Java Server Page) Lucene Index for documents keyword related documents SemDis API gets the types of the instance term from the ontology. Ontology SemDis API

  14. Questions, Comments Email: bilalgonen@gmail.com Web: www.bilalgonen.com Thank you…

More Related