News

The know-it-all mobile: coming "soon" courtesy Wolfram?

by Guy J Kewney | posted on 09 March 2009


"Tantalising" doesn't come close. "All one needs to be able to do is to take questions people ask in natural language, and represent them in a precise form that fits into the computations one can do." That's "all" huh?

The dream is of a system which will hear what you say, and find answers. Not search pages with the words you used on them; real answers.

So, if I type in "How likely is another Tunguska incident?" I'm certainly NOT looking for five thousand links to web pages featuring "likely" and "another" and "Tunguska" and "incident" respectively. What I want is a response which knows that the Earth just got missed by another Tunguska-sized asteroid, and how much damage that caused, and whether I should dig a deep shelter.

That, says Stephen Wolfram, is exactly what he has nearly got. "In just two months it’s going to be going live," his blog reveals of Wolfram\Alpha - which will understand natural language queries, and know how to process them.

Normally, I'd dismiss this as another pipe-dream, doomed to frustrating failure along with that fridge addon which knows what food is in there and what would be a good recipe using those ingredients, or "what colour should the wheel be?" - but a colleague of mine has seen it and tweets that "it could be The Next Thing!" in some excitement. He rarely gets excited about things that Don't Matter... so it's probably worth passing on.

Wolfram himself says:

I wasn’t at all sure it was going to work. But I’m happy to say that with a mixture of many clever algorithms and heuristics, lots of linguistic discovery and linguistic curation, and what probably amount to some serious theoretical breakthroughs, we’re actually managing to make it work.

Pulling all of this together to create a true computational knowledge engine is a very difficult task.

It’s certainly the most complex project I’ve ever undertaken. Involving far more kinds of expertise—and more moving parts—than I’ve ever had to assemble before.

And—like Mathematica, or NKS—the project will never be finished.But I’m happy to say that we’ve almost reached the point where we feel we can expose the first part of it.

Watch for more on the (going to be) website


Technorati tags:   
Ask me anything! twitter: gkewney - You can discuss this article on our discussion board.