Wolfram Alpha: Next major search breakthrough?

MrBrian · Mar 9, 2009

Wolfram Alpha: Next major search breakthrough?

In May, Wolfram will unveil his latest creation, now called Wolfram Alpha. It applies his work with Mathematica and NKS (A New Kind of Science) to Web search. "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 in a recent blog post. "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...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," he added.
Click to expand...

Wolfram Alpha is Coming -- and It Could be as Important as Google

In a nutshell, Wolfram and his team have built what he calls a "computational knowledge engine" for the Web. OK, so what does that really mean? Basically it means that you can ask it factual questions and it computes answers for you.

It doesn't simply return documents that (might) contain the answers, like Google does, and it isn't just a giant database of knowledge, like the Wikipedia. It doesn't simply parse natural language and then use that to retrieve documents, like Powerset, for example.

Instead, Wolfram Alpha actually computes the answers to a wide range of questions -- like questions that have factual answers such as "What is the location of Timbuktu?" or "How many protons are in a hydrogen atom?," "What was the average rainfall in Boston last year?," "What is the 307th digit of Pi?," "where is the ISS?" or "When was GOOG worth more than $300?"
Click to expand...

EASTER · Mar 10, 2009

Thanks for your Topic and summary. This might prove very encouraging, not to downplay Google by any stretch, but it appears to been well thought out.

We'll all be looking forward to trying this one.

MrBrian · Mar 10, 2009

You're welcome EASTER

A competitor that can be used now with registration is http://www.trueknowledge.com/. Here are comments, purportedly from the founder of True Knowledge, about Wolfram Alpha (taken from http://www.techcrunch.com/2009/03/0...to-factual-questions-this-is-going-to-be-big/):

William Tunstall-Pedoe - March 8th, 2009 at 10:05 pm PDT

I’m the founder of True Knowledge and Stephen Wolfram was good enough to give me an extended demo of Wolfram Alpha over the weekend.

I’d agree that we are possibly the closest comparable in that we are also building a platform that unifies and stores structured knowledge and enables this knowledge to be accessible through question answering. We also heavily use inference to “compute” answers.

Having said that, there are also considerable differences: Wolfram’s broad approach is bringing together and curating all the knowledge themselves and generating a full page response to queries using millions of lines of Mathematica code.

Our approach in contrast is to enable users to build the knowledge base and to produce concise answers created by inference steps that usually involve no domain specific coding at all.

There are advantages and disadvantages of both these approaches and these will also heavily affect the likely uses the systems will be put to. However, it was very exciting to see WA and I’m looking forward to the launch.
Click to expand...

MrBrian · Mar 10, 2009

A competitor is START from MIT, which has been available since 1993. START, however, seems limited compared to what Wolfram Alpha might be able to do.

MrBrian · Mar 10, 2009

Doug Lenat, the founder of the Cyc project, has written a new comment at the twine.com URL mentioned in my first post:

Stephen Wolfram generously gave me a two-hour demo of Wolfram Alpha last evening, and I was quite positively impressed. As he said, it's not AI, and not aiming to be, so it shouldn't be measured by contrasting it with HAL or Cyc but with Google or Yahoo. At its heart is a formal Mathematica representation. Its inference engine is basically a large number of individually hand-engineered scripts for tapping into data which he and his team have spent the last several years gathering and "curating". For example, he has assembled tables of historical financial information about countries' GDP's and about companies' stock prices. In a small number of cases, he also connects via API to third party information, but mostly for realtime data such as a current stock price or current temperature. Rather than connecting to and relying on the current or future Semantic Web, Alpha computes its answers primarily from his own curated data to the extent possible; he sees Alpha as the home for almost all the information it needs, and will use to answer users' queries.

In an important sense, Alpha is a logical extension of Mathematica: it extends the range of types of information for which significant power can be gained by manually, and exhaustively, enumerating a large set of cases: airplane designs, cities, currencies, etc. I.e., Alpha extends what Mathematica has done previously for things like chemical compounds, geometric surfaces, topological configurations, arithmetic series, trigonometric ratios, and equations. In the new cases, as Mathematica did in those abstract math cases, Alpha excels at not just retrieving the stored data but performing various appropriate numeric calculations on the data, and displaying the results in beautiful graphs and easily comprehended tables for the user. The resulting mosaic covers a large portion of the space of queries that the average person might genuinely want to ask, in the course of their day. The interface is not exactly natural language, but can be treated by the user as though it were -- just as users of browsers can treat them as though they parsed sentences even though they don't. A better way to think of it is a DWIMM ("do what I might mean"), so if you type in something like "gdp France / Germany", it calculates and returns a graph of the relative fraction of France's annual GDP to Germany's GDP, over the last 30 years or so. If you just type in "gdp", it looks up your local host and (in my case) displays the GDP of the USA over the last 30 years, plus various pieces of information about what gross domestic product is, from a mathematical formula perspective but not from a semantic one. It does not have an ontology, so what it knows about, say, GDP, or population, or stock price, is no more nor less than the equations that involve that term.
Click to expand...

...

The bottom line is that there are a large range of queries it can't parse, and a large range of parsable queries it can't answer even when it can answer the constituents out of which they should be answerable, but it handles a huge range of numeric and scientific queries correctly even in its current state. And Dr. Wolfram and his team are chipping away at the natural language blocks, at the holes in the curated data repository, and at increasing the type and depth of logical combination of constituents, one by one, in priority order, just as they should.
Click to expand...

EASTER · Mar 11, 2009

Interesting concept and read without a doubt.

It remains to be seen, and maybe soon that this will extend Mathematica into an ever more desired measure of advanced information that can be put to some real use and fan out to expand it's interest in ways not yet conceived.

Thanks

EASTER

MrBrian · Apr 26, 2009

Public preview streamed on Web live on Tue at 3PM USA Eastern time.

Defcon · Apr 26, 2009

Interesting topic! There's no doubt search needs to expand beyond the simple pattern matching that all current search engines use. Google innovation was page ranking, which allows them to filter results and find the most relevant ones, but in essence its just running a massive string compare against its cached copies of web pages.

Understanding the semantic nature of content and extracting meaning from it is a very hard AI problem. If we are truly close to solving it (which I don't believe) it will mean wonders, not just for web search, but local documents, linking together content in a more useful way than hyperlinks, and all sorts of possibilities.

ronjor · May 5, 2009

Screenshots: A tour of Wolfram Alpha

MrBrian · May 16, 2009

Officially launches May 18, but may be available to a limited extent before then. I'm using it right now in fact . Its availability is sporadic now though.

http://www.wolframalpha.com/

Coolio10 · May 16, 2009

MrBrian said:

Officially launches May 18, but may be available to a limited extent before then. I'm using it right now in fact . Its availability is sporadic now though.

http://www.wolframalpha.com/
Click to expand...

Too much traffic, won't load!

ambient_88 · May 16, 2009

So far, I am liking Wolfram Alpha. It is especially strong when it comes to computing mathematical equations (not surprise there as the engine is Wolfram Mathematica).

Fontaine · May 16, 2009

Coolio10 said:

Too much traffic, won't load!
Click to expand...

Agree. I can load the page, but when I click any links, Firefox stops responding and then crashes. Will have to wait a few days and then give it a shot.

TonyW · May 17, 2009

A lot of it appears to be computational reference, which is useful when you need information using numerical facts.

I have looked at the examples, and it appears you can get dictionary definitions, but it's obviously not complete yet. Try 'word thixotropy' and WolframAlpha doesn't know that one.

MrBrian · May 24, 2009

Wolfram Alpha searching for its niche

We asked readers to give us their impressions of Wolfram Alpha following its debut last Friday, and the results were not good. Asked to judge how happy they were with the outcome of their searches, readers gave Wolfram Alpha an average score of 3.55, with 1 being "most satisfied" and 5 being least.

For the most part, readers were dissatisfied with Wolfram Alpha's ability to produce results for anything outside of a relatively narrow set of queries related to math, science, or statistics. Forty percent said they would not recommend Wolfram Alpha to friends, while 28 percent thought it was only appropriate for "serious data nerds." (Percentages based on 1,459 responses.)
Click to expand...

Log in or Sign up

Wolfram Alpha: Next major search breakthrough?

MrBrian Registered Member

EASTER Registered Member

MrBrian Registered Member

MrBrian Registered Member

MrBrian Registered Member

EASTER Registered Member

MrBrian Registered Member

Defcon Registered Member

ronjor Global Moderator

MrBrian Registered Member

Coolio10 Registered Member

ambient_88 Registered Member

Fontaine Registered Member

TonyW Registered Member

MrBrian Registered Member

Log in or Sign up

Wolfram Alpha: Next major search breakthrough?

MrBrian Registered Member

EASTER Registered Member

MrBrian Registered Member

MrBrian Registered Member

MrBrian Registered Member

EASTER Registered Member

MrBrian Registered Member

Defcon Registered Member

ronjor Global Moderator

MrBrian Registered Member

Coolio10 Registered Member

ambient_88 Registered Member

Fontaine Registered Member

TonyW Registered Member

MrBrian Registered Member

Useful Searches