# Opinion: Wolfram Alpha: How does it work?

## E-commerce

### RELATED TOPICS

Dr. Peet Morris is an expert in software engineering, computational linguistics, and statistics. Here he explains how Wolfram Alpha works.

As there's been a lot of talk linking Wolfram Alpha with Google lately, let's start this 'how it works' hypothesis with a simple comparison.

In a sense, you can think of Wolfram Alpha as a kind of 'super' version of Google's Calculator.

If you don't know about Google's Calculator, go to Google's homepage, and enter '8 nautical miles in chains' - you'll see that the answer is 736.498847 (and if a 'chain' is an unknown to you - well, you've at least two places to look for it now).

So now, let's enter the same query in Wolfram Alpha.

You'll also notice that Wolfram Alpha has 'rounded up', and has assumed that we're not too concerned with the missing inch!

Like Google, Wolfram Alpha has carried out some sort of look-up to find out what a 'nautical mile' and a 'chain' have in common; and it's discovered that they're units of measurement (the probable key word is 'mile' here).

Wolfram Alpha then carried out some syntactic and semantic analysis on the sentence as a whole, and came to the conclusion that we'd like to know one (times eight), converted to the other. Apart from giving us some extra handy data, Google has done more or less the same thing.

Now, let's take another example.

If we enter; 'distance between urbana and champaign' (proper-case omitted on purpose here - no hints given and none appreciated) into Google, we find that Google's Calculator can't help.

Google, and as you might expect, gives us a bunch of results drawn from web-text. The first result I got when I actually did this was taken from WikiAnswers where someone asked 'What is the driving distance between Chicago Illinois and Champaign Urbana Illinois?' - which is not what we're interested in. Result: there's no immediately obvious and satisfactory answer from a Google search for this query.

OK, now let's try Wolfram Alpha.

You'll see from the output that Wolfram Alpha has assumed that, maybe because they're rather close together, we're asking about suburbs of Illinois (which I was). And, having given that a high probability, with a little semantic analysis, it has assumed that we'd like to know the distance between those two places (which I did); and you can see the result.

So, how did Wolfram Alpha do it?

This is where we need to come back to the vague term I used previously - look-up.

Google, as far as we're concerned, gets its data from the public domain, that is, from what's on the public web.

On the other hand, Wolfram Alpha gets its data from the 'Deep Web'. That's data sources that either require a subscription, or at least some sort of entry point (an account maybe). In simple terms, some are free, and some are 'fee' (guess which is more robust, structured and reliable).

Considering our latest query, here is a partial list of data sources that might have been employed/analysed to answer our 'distance between urbana and champaign' query.

Wolfram Alpha exploits data sources to determine links (relationships is probably a more accurate word) between search-terms, and, more importantly, how the likely important terms (might) relate to one another.

The words used in a query could supply Wolfram Alpha (more so in Wolfram Alpha than in Google say) with some useful hints - for example the preposition 'between' is certainly more interesting than verb 'driving'; and this is the part of the Wolfram Alpha-engine where I suspect Mathematica (the language the whole platform is written in) really earns its corn (the whys and wherefores are outside of the space provided here).

Now to the bottom line: As to how all this works (Google/Wolfram Alpha) in detail - well, we don't really know (secrets and all). However, I for one suspect that at Wolfram Alpha there's a rather clever ontological-database at work here. Indeed, one that will learn and evolve as more data is fed into it, and given that it has the right rules to link it all up.

So, there you go - not really an in-depth look at Wolfram Alpha and what you can do with it, but hopefully something that will at least go someway to showing how Wolfram Alpha isn't what we commonly call a 'search engine'. Next time I'll give you a detailed example of how Wolfram Alpha can pull together some really useful statistics.

By the way, I'll tell you why I used those two suburbs (Urbana and Champaign). One is where HAL (you know, 2001 and all that) was activated, whilst the other is where Wolfram Alpha did the very same thing.

Dr. Peet Morris studied Software Engineering, Computational Linguistics, and Statistics at the University of Oxford. He is currently a researcher in the Department of Experimental Psychology, and a College Lecturer in Statistics at St. Hilda's College.

This was last published in May 2009

## Features

Enjoy the benefits of CW+ membership, learn more and join.

#### Start the conversation

Send me notifications when other members comment.

## SearchCIO

• ### CISOs, give your cybersecurity program a sense of purpose

'Vanquish the enemy you can see … then prepare for the next engagement.' Brooks Brothers' Phillip Miller gives fellow CISOs new ...

• ### Who's talking? Conversational agent vs. chatbot vs. virtual assistant

Think a conversational agent, chatbot and virtual assistant are the same? Think again. IBM Watson VP and CTO Rob High explains ...

• ### Neurala claims 'lifelong deep neural nets' don't forget

Boston startup Neurala says it has developed deep neural networks that can learn on the fly. Neurala's COO Heather Ames explains.

## SearchSecurity

• ### Olympic Destroyer malware more complex than first thought

News roundup: The Olympic Destroyer malware is more sophisticated than researchers first thought. Plus, Microsoft looks to change...

• ### SonicWall spots Meltdown exploits with machine learning tech

SonicWall says its new deep memory inspection technology, which powers the vendor's Capture Cloud sandbox service, can block ...

• ### Intel bug bounty programs widened after Meltdown and Spectre

Intel's bug bounty program expanded its scope and rewards for bugs across all Intel products, and the company added a new program...

## SearchNetworking

• ### Cisco revenue turns positive, as software, security sales up

Cisco revenue grew last quarter for the first time in more than two years, due, in part, to rising software sales. But analysts ...

• ### Making the most of incident detection and response

This week, bloggers look into incident detection strategies, a new anomaly detection tool from ExtraHop and how Ethernet VPN ...

• ### Latest Juniper switches up throughput for cloud applications

The latest Juniper switches target companies that want a network infrastructure with the throughput and management software to ...

## SearchDataCenter

• ### Evaluate read-intensive and write-intensive SSD use cases

Consider write wear, performance and other factors when choosing between read-intensive, write-intensive and mixed-use ...

• ### Some hyper-converged infrastructure use cases pose pitfalls

Hyper-converged infrastructure adoption is skyrocketing, but that doesn't mean that the technology is the best choice for every ...

• ### Dell hyper-converged reorg streamlines products, ups CI odds

Market pressures and manufacturing synergies drove Dell to integrate its HCI and CI products with its core business units, but ...

## SearchDataManagement

• ### Hyperledger Fabric offers path to enterprise blockchain future

Blockchain arose from bitcoin, but it's looking to find a place in the enterprise. Frameworks like Hyperledger Fabric could ...

• ### MongoDB 4.0 takes ACID transactions to multi-document level

MongoDB is taking a deeper step into SQL-style processing waters with a 4.0 update that brings increased support for ...

• ### Data lake concept needs firm hand to pay big data dividends

Data lakes pose technology deployment and data management challenges that can leave analytics users high and dry if the ...

Close