NELL: A CMU Research Project To Read The Web

A place to discuss the science of computers and programs, from algorithms to computability.

Formal proofs preferred.

Moderators: phlip, Moderators General, Prelates

User avatar
DorkRawk
Posts: 51
Joined: Thu Mar 08, 2007 6:50 am UTC
Location: Chicago
Contact:

NELL: A CMU Research Project To Read The Web

Postby DorkRawk » Tue Oct 12, 2010 4:39 pm UTC

I just saw an article about this project today. Basically it does natural language processing on a large chunk of the web in order to develop "ideas" based on provided categories and relations. It looks really cool and seems to be producing reasonable results. It's pretty impressive to see this mix of NLP, data mining, and reasoning in action.

Here's a link to the project page: http://rtw.ml.cmu.edu/rtw/

squareroot
Posts: 548
Joined: Tue Jan 12, 2010 1:04 am UTC
Contact:

Re: NELL: A CMU Research Project To Read The Web

Postby squareroot » Tue Oct 12, 2010 11:28 pm UTC

WTF: It's a sport now!

That's a pretty cool project. I wonder how it gets the predicates?

Oh btw - it says there's a 50% chance Google currently owns Apple. :D

EDIT: And Harry Truman is president! Corals eat fish - not the other way around - and Morgan freeman is female now!
<signature content="" style="tag:html;" overused meta />
Good fucking job Will Yu, you found me - __ -

userxp
Posts: 436
Joined: Thu Jul 09, 2009 12:40 pm UTC

Re: NELL: A CMU Research Project To Read The Web

Postby userxp » Wed Oct 13, 2010 3:15 pm UTC

These knowledge bases are really cool. If only we had any use for them...

User avatar
BlackSails
Posts: 5315
Joined: Thu Dec 20, 2007 5:48 am UTC

Re: NELL: A CMU Research Project To Read The Web

Postby BlackSails » Fri Oct 15, 2010 7:22 pm UTC

"the companies news and drudge_report compete with eachother "

lolololl

Also, things like "trinidad is a city located in the state or province colorado"


Return to “Computer Science”

Who is online

Users browsing this forum: No registered users and 9 guests