I have a project where i need to build a semantic search system. the system will consist of an ontology. It is a semantically enriched information system. My current issue is i need to find such an area where sufficient modelling can be made to prove the use of ontology can improve in recall and precision. The area need to be quite specific and if existing ontologies is already available, i can just grab them and use them.

Currently I'm thinking of using Natural Photos containing animals. The thing about it is that the photo has a place, so i can get an ontology of countries and captural taxonomical links. Then i'll have an animal and i can get an ontology of animal and use it.

Any other suggestion i can consider, a different area??

asked 17 Feb '13, 19:32

Noor's gravatar image

Noor
415
accept rate: 0%


The color-coded version of the Linked Data Cloud at http://lod-cloud.net/versions/2011-09-19/lod-cloud_colored.html gives you an idea of what domains have how much data (and usually, accompanying ontologies), so that would be worth exploring before you start your actual work.

link

answered 20 Feb '13, 12:33

bobdc's gravatar image

bobdc
3.8k7
accept rate: 14%

Your answer
toggle preview

Follow this question

By Email:

Once you sign in you will be able to subscribe for any updates here

By RSS:

Answers

Answers and Comments

Markdown Basics

  • *italic* or _italic_
  • **bold** or __bold__
  • link:[text](http://url.com/ "Title")
  • image?![alt text](/path/img.jpg "Title")
  • numbered list: 1. Foo 2. Bar
  • to add a line break simply add two spaces to where you would like the new line to be.
  • basic HTML tags are also supported

Tags:

×596
×15

Asked: 17 Feb '13, 19:32

Seen: 398 times

Last updated: 20 Feb '13, 12:33