Wolfram Alpha "Computational Knowledge" Search Engine Is Coming
Stephen Wolfram, the developer of the popular Mathematica software, plans to release an intelligent search engine in the following months, the Wolfram Alpha.
The ambitious project will take advantage of a mixture of many clever algorithms and heuristics to offer a search engine that will not just index the information available on the web today seeking for text, but also applies computational knowledge and some artificial intelligence before returning the search queries.
Wolfram believes that his approach would deliver a system that could give a correct answer to any factual question. While currently available search engines provided a tremendous amount of information, they fail to compute from that. And in effect, these search engines can only answer questions that have been literally asked before.
"We can look things up, but we can?t figure anything new out," Wolfram wrote at its blog.
"So how can we deal with that? Well, some people have thought the way forward must be to somehow automatically understand the natural language that exists on the web. Perhaps getting the web semantically tagged to make that easier," Wolfram added.
Wolfram's knowledge though its current projects - Mathematica and NKS - has helped him realize that there?s another way that would help the system return information efficiently: to explicitly implement methods and models, as algorithms, and explicitly curate all data so that it is immediately computable.
Wolfram admits that the Alpha project is very complicated, but he said that he had succeeded in creating a system that just "knows a lot".
"Every different kind of method and model?and data?has its own special features and character. But with a mixture of Mathematica and NKS automation, and a lot of human experts, I?m happy to say that we?ve gotten a very long way,"
Wolfram also claims that by making the knowledge computable, the system could easier and more efficiently recognize and reply to the search queries without needing to actually know the natural language of the users.
Another problem in Wolfram's approach was the way the search engine would understand people's input.
"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," Wolfram said.
"Of course, even that has never been done in any generality. And it?s made more difficult by the fact that one doesn?t just want to handle a language like English: one also wants to be able to handle all the shorthand notations that people in every possible field use," he added.
Being the most complex project Wolfram has ever undertaken, he has almost reached the point where it can be exposed. The search engine will go live in May. For now, you can visit http://www.wolframalpha.com/.
Wolfram believes that his approach would deliver a system that could give a correct answer to any factual question. While currently available search engines provided a tremendous amount of information, they fail to compute from that. And in effect, these search engines can only answer questions that have been literally asked before.
"We can look things up, but we can?t figure anything new out," Wolfram wrote at its blog.
"So how can we deal with that? Well, some people have thought the way forward must be to somehow automatically understand the natural language that exists on the web. Perhaps getting the web semantically tagged to make that easier," Wolfram added.
Wolfram's knowledge though its current projects - Mathematica and NKS - has helped him realize that there?s another way that would help the system return information efficiently: to explicitly implement methods and models, as algorithms, and explicitly curate all data so that it is immediately computable.
Wolfram admits that the Alpha project is very complicated, but he said that he had succeeded in creating a system that just "knows a lot".
"Every different kind of method and model?and data?has its own special features and character. But with a mixture of Mathematica and NKS automation, and a lot of human experts, I?m happy to say that we?ve gotten a very long way,"
Wolfram also claims that by making the knowledge computable, the system could easier and more efficiently recognize and reply to the search queries without needing to actually know the natural language of the users.
Another problem in Wolfram's approach was the way the search engine would understand people's input.
"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," Wolfram said.
"Of course, even that has never been done in any generality. And it?s made more difficult by the fact that one doesn?t just want to handle a language like English: one also wants to be able to handle all the shorthand notations that people in every possible field use," he added.
Being the most complex project Wolfram has ever undertaken, he has almost reached the point where it can be exposed. The search engine will go live in May. For now, you can visit http://www.wolframalpha.com/.
