Main Page > Knowledge Extractor

Project

  • Started: June 2009
  • Goal: Extract knowledge from text-based sources like Wikipedia in a format that can be queried for meaningful information.


Resources


Current Status

9/10/09 Please note that you will need an ACM account to edit this wiki or our SVN repository.

8/30/09 New "tickets" have been posted for people to work on. Today's focus has been preparing for ACM Open House.

7/23/09 Meeting with Prof. Amir to discuss ideas for 0.2.

7/19/09 Updates to 0.1 (learning more facts).

7/17/09 Version 0.1 was completed last night. The website looks great and processes simple queries. The back end takes the raw XML and turns it into sentences, which then get chunked into bite-size morsels of information and inserted into the database. We will be discussing our goals for version 0.2 at our next meeting.

6/12/09 Working on version 0.1 which will include a website querying an SQL database filled with parsed sentences from Simple Wikipedia.


Contact Information

If you have ideas for the project, need to contact the people in charge, or simply want more information, see the contact page on our main website.


Attachments