Changing The World Of Internet Search Forever -- Again

It's not every day that you hear of web software that "could change the Internet forever" -- unless, of course, part of your job is to take phone calls from web software vendor marketing executives.

Still, this article in Sunday's Independent newspaper caught my eye because of my interest in the evolution of search technology. It's about Wolfram Alpha, a new Internet search engine that promises to give users definitive answers to specific questions, rather than pages of links from which the sought-after information might be found (which is what we get from Google now). Independent writer Andrew Johnson adds:

[I]t will also produce a neat page of related information – all properly sourced – such as geographical location and nearby towns, and other mountains, complete with graphs and charts.

The real innovation, however, is in its ability to work things out "on the fly," according to its British inventor, Dr Stephen Wolfram. If you ask it to compare the height of Mount Everest to the length of the Golden Gate Bridge, it will tell you. Or ask what the weather was like in London on the day John F. Kennedy was assassinated, it will cross-check and provide the answer. Ask it about D sharp major, it will play the scale. Type in "10 flips for four heads" and it will guess that you need to know the probability of coin-tossing. If you want to know when the next solar eclipse over Chicago is, or the exact current location of the International Space Station, it can work it out.

Dr Wolfram, an award-winning physicist who is based in America, added that the information is "curated", meaning it is assessed first by experts. This means that the weaknesses of sites such as Wikipedia, where doubts are cast on the information because anyone can contribute, are taken out. It is based on his best-selling Mathematica software, a standard tool for scientists, engineers and academics for crunching complex maths.

I wonder what the implications of Wolfram Alpha are for the ubiquitous "ego search." Maybe you find out what people really think of you. Already there's a downside.

More importantly, the article had me wondering how -- or if -- Wolfram Alpha bore any relationship to Semantic Web technology, for which we've dedicated a Web site and conference. The Independent article doesn't address this, but I found an article on TechCrunch from Nova Spivak, CEO of Radar Networks, that does. Spivak wrote his piece after spending two hours talking to Wolfram and viewing demonstrations of the new search engine. Some excerpts:

There is no reason that one MUST use the Semantic Web stack to build something like Wolfram Alpha. In fact, in my opinion it would be far too difficult to try to explicitly represent everything Wolfram Alpha knows and can compute using OWL ontologies. It is too wide a range of human knowledge and giant OWL ontologies are just too difficult to build and curate.

It would of course at some point be beneficial to integrate with the Semantic Web so that the knowledge in Wolfram Alpha could be accessed, linked with, and reasoned with, by other semantic applications on the Web, and perhaps to make it easier to pull knowledge in from outside as well. In this area, the standards of the Semantic Web could be quite useful to the project. However for the internal knowledge representation and reasoning that takes places in the system, it appears Wolfram has found a pragmatic and efficient representation of his own, and I don't think he needs the Semantic Web at that level. It seems to be doing just fine without it.

What I glean from this is that Wolfram Alpha and the Semantic Web are two different animals that could work together, but don't necessarily need to at the moment. (If someone else has a different interpretation, by all means leave a comment.) It will be interesting to see how this plays out.