Topic: Wolfram Alpha: A Test Run

[Samker]

http://www.wolframalpha.com/



Wolfram Alpha is online for testing throughout the weekend, in anticipation of the online knowledge base officially going live on Monday. Although the launch team warned in the Wolfram Alpha Blog that the site may go down periodically throughout the weekend, anyone has a chance to check out how well it answers fact-based questions from its database of information organized by Wolfram Alpha staff.

How well does it work? Well, it was able to find quickly how many calories are in a serving of cocoa puffs, what day of the week I was born on, and PC World's circulation. Entering "Star Trek" automatically pulled up the J.J. Abrams film and told me it was released 0.022 years ago.

Besides providing information on search terms, Wolfram does a great job at conversions and answering equations. I was able to convert the value of my pocket change from dollars to yen and figured out what a 20 percent tip would be for a $25.86 meal and how to break that tip up into currency.

At the bottom of the page you can take a look at the sources Wolfram has drawn from to answer questions about your topic, or save your results as a PDF. The PDF is basically a reproduction of the Web site; it would be nice if it was reworked in the future to be more printer-friendly.

I was quickly impressed with the site's capability to return relevant information about my search terms just as fast as Google would refer me to a list of indexed sites. I couldn't help but try to push Wolfram to its limits.

Working Wolfram

I started simple. I entered: How old is the oldest person? After I pressed enter, the logo above the search bar animated to show the site was churning through information. In less than a second, Wolfram gave me the name Jeanne Louise Calment, the oldest person ever recorded, who is 122.45 years old. It then broke that time down into days, centuries, seconds, anomalistic, and sidereal years.



Throughout the process I would occasionally get an error message from the site: "I'm sorry Dave, I'm afraid I can't do that..." to notify me that the site has exceeded its test load. The amusement of the "2001: A Space Odyssey" reference wore off after seeing it numerous times, but I ws typically able to resume searching within a few seconds of receiving the message.

As I continued to use the site it seemed Wolfram performed nicely, but when I asked it how much money Star Wars Episode 1 made its opening weekend Wolfram wasn't able to provide results. After a second of "thinking" it recommended the search term "Star Wars Episode 1." I clicked and it brought me to a page that displayed the movie length, cast, release date, and total box office numbers, but not the totals for opening weekend.

Work in Progress

It seems at the moment Wolfram is better at directing you to information if you stick to search terms instead of questions. And unfortunately for PC World readers and tech junkies alike, product information is not available yet.

Instead of leading me to a well-laid-out spreadsheet of juicy rumors, my search for iPhone brought me to a page that said "development of this topic is under investigation." A search for Blackberry Storm led me to two pages: one about food and the other about meteorology.

All things aside, Wolfram Alpha is performing nicely, considering this is a test weekend. The tool may be able to better address some of my more abstract questions in the weeks to come.

If you haven't gotten a chance to visit Wolfram yet, do it now. Let us know what you think??



(PCW)

[saradhi]

Mathematica has been a great success in very broadly handling all kinds of formal technical systems and knowledge.

But what about everything else? What about all other systematic knowledge? All the methods and models, and data, that exists?

Fifty years ago, when computers were young, people assumed that they’d quickly be able to handle all these kinds of things.

And that one would be able to ask a computer any factual question, and have it compute the answer.

But it didn’t work out that way. Computers have been able to do many remarkable and unexpected things. But not that.

I’d always thought, though, that eventually it should be possible. And a few years ago, I realized that I was finally in a position to try to do it.

I had two crucial ingredients: Mathematica and NKS. With Mathematica, I had a symbolic language to represent anything—as well as the algorithmic power to do any kind of computation. And with NKS, I had a paradigm for understanding how all sorts of complexity could arise from simple rules.

But what about all the actual knowledge that we as humans have accumulated?

A lot of it is now on the web—in billions of pages of text. And with search engines, we can very efficiently search for specific terms and phrases in that text.

But we can’t compute from that. And in effect, we can only answer questions that have been literally asked before. We can look things up, but we can’t figure anything new out.

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.

But armed with Mathematica and NKS I realized there’s another way: explicitly implement methods and models, as algorithms, and explicitly curate all data so that it is immediately computable.

It’s not easy to do this. 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.

But, OK. Let’s say we succeed in creating a system that knows a lot, and can figure a lot out. How can we interact with it?

The way humans normally communicate is through natural language. And when one’s dealing with the whole spectrum of knowledge, I think that’s the only realistic option for communicating with computers too.

Of course, getting computers to deal with natural language has turned out to be incredibly difficult. And for example we’re still very far away from having computers systematically understand large volumes of natural language text on the web.

But if one’s already made knowledge computable, one doesn’t need to do that kind of natural language understanding.

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.

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.

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.

It’s going to be a website: www.wolframalpha.com. With one simple input field that gives access to a huge system, with trillions of pieces of curated data and millions of lines of algorithms.

We’re all working very hard right now to get Wolfram|Alpha ready to go live.

I think it’s going to be pretty exciting. A new paradigm for using computers and the web.

That almost gets us to what people thought computers would be able to do 50 years ago.

[Anton]

Cool!