Radar Networks attracted a fair degree of attention with their roll-out of Twine, and the company's CEO has built a reputation as one of the more thoughtful thinkers in the space. Nova took to the stage at the Semantic Technology Conference today, not to talk about his own company or ideas, but to lead a conversation with Russell Foltz-Smith from Wolfram Research.
Wolfram Research, of course, is the company behind the recently launched Wolfram Alpha; a 'computational knowledge engine' that attracted a wave of attention that reached into the mainstream media.
"Putting all of the world's computable knowledge; it sounds impossible... or over-confident, maybe. What is computable knowledge?"
"It's 'systematic knowledge.' It can be compared, contrasted, correlated, computed on. It's not a movie review. Examples are classical physics, financial data and models, weather data and models... It's not the latest opinion on who Britney Spears is dating. We don't have a model to do anything with that in our system."
Nova asks if it's the difference between objective and subjective... Alpha deals with objective information. 'Facts,' almost?
Nova asks about sources, pointing to the example of Tibet; is it a 'fact' that Tibet that is part of China, or not... ?
"In the case of geo-political things, and religious things, we have to make choices... and allow the community to let us know whether they agree or not..." Couldn't the system represent multiple views, tied to the diverse sources? Could we not show the different opinions, and allow the user to make informed decisions themselves?
Nova; "is the world's computable knowledge infinite?"
Russell; "the foundation of computable knowledge is likely to be finite... The amount of knowledge that can be computed and generated from that is infinite..."
Nova; "I can see that maths could be finite. But geopolitics, health, etc... that's much, much larger..."
Russell; "The instances seem very complex... Huge, but finite... I don't want anyone to think we'll have this done in ten years... It's a long term thing."
Nova; "Stephen [Wolfram] reckons it could be done in three years...?"
Nova; "Looking at the back end, the ontology seems to be implicit. I didn't see any classes, just a lot of instances... a set of facts. As the team grows, how do you prevent people adding facts in different ways?"
Russell; "There are a set of stored facts; things you know about a city. But then there are computed facts that you couldn't store in a traditional ontology." Huh?
Nova; "Can you make a statement about what percent of the world's computable knowledge is there today?"
Russell; "I can't make a statement..."
Nova; "The syntax is quite interesting... but enigmatic. It wasn't necessarily that the knowledge wasn't there, but that I'd asked for it in the wrong way. Can't you make a manual? ... Stephen [Wolfram] said it would be an impossible task to write the manual... or to make a generic natural language on top."
Nova; "In some cases a naive query will get you the answer, but maybe there's a need for a layer that helps you when you don't get what you want..."
Russell; "I think we're getting close... we're going to put an API out in the next few weeks, and hopefully someone will build the application using that to parse natural language and translate it for Alpha... Do we spend our time doing that, or putting more data and more models into the system... I reckon our time is best spent adding more data..."
Nova; "Is there a set of schemas or ontologies to link all of this stuff together?"
Russell; "There isn't an ontology over the whole system... but within a domain there is structure... Is there some grand scheme that we have internally? Not really. The company has been doing this stuff for 23 years, so there's a bit of a shared understanding internally."
Examples keep coming back to mathematics... To succeed, Alpha has to offer compelling examples that are far broader...
Nova; "What about reasoning. You've said that you can derive additional knowledge. What kinds of reasoning is the system capable of?"
Russell; "I'd call it very simple reasoning. For example changing the currency based upon your geo-location... Is there any weak or strong AI in here? Not really. Could you build something like that? Probably. Will we? I don't know..."
Nova; "Alpha seems to be a subset of Mathematica capabilities... Would you expand that, and bring a full Mathematica to the Web"
Russell; "It is, and there are plans to extend the capabilities. I don't know if we'd go to a full-blown Mathematica on the web."
Russell's mentioning a subscription service for people working with more data, or needing more compute time. The public web site tends to time out a query in 4-8 (or 48?) seconds... The professional subscription version will have a monthly subscription version that will allow you to compute bigger questions. There will also be a pay-per-use API... and 'primitive' advertising. More advanced advertising, based on transactions, to be launched soon.
Nova; "Alpha's really cool, but I want to do this on my own knowledge... inside an enterprise, inside a government agency..."
Russell; "We can roll out a custom Wolfram Alpha for those who want it behind the firewall. We will also let people upload their own data sets. We need to find a sensible way to let people do this..."
Nova; "There was a lot of hype - possibly my fault - around Alpha being a Google Killer. Obviously it's not that. It's something quite different. Who is the user, and what are they using it for?"
Russell; "Use will evolve, and it already has. There's an obvious use by students, but the school year has just ended.
Nova; "Wolfram Alpha; now even Ph.D's can cheat on their homework." :-)
Nova; "Are consumers using it? Obviously they're having a play, but are they coming back and using it?"
Russell moves off to talk about academic use... Dodging the question?
Nova; "Are the financial capabilities in Alpha differentiated from the capabilities banks and investors already have in their vertical?"
Russell; "more sophisticated than a general finance web site, but probably less sophisticated than you'd find on a terminal in a bank."
Nova; "Do I really need to know how long it would take an ant to get from San Francisco to Cairo?"
Russell; "Because of the way the system is engineered, it just keeps computing until it runs out of time. With simple queries you'll get a lot of data. It just keeps computing."
Nova; "What's the big challenge, moving forward?"
Russell; "Setting priorities."
Nova; "So let's talk about Google. They made some aggressive marketing moves during the Alpha roll-out, and they're continuing to roll products out to chip away... Do you think that what you've built is defensible, just because it's hard... or can you defend it in other ways?"
Russell; "There are significant barriers to what we're doing. Someone else could build this... but would they want to? That's an open question."
Nova; "Do you hope to work with other companies? Perhaps revenue share with them?"
Nova; "There's been a lot of interest in how Alpha might connect with open standards and the Semantic Web..."
Russell; "If you want the platform to be used, we'll have to do some of this stuff... RDF, OWL, etc could play a huge role."
Russell; "It'll depend on pick-up of the API... which is due out in a few weeks."
Nova; "So what's the implication for education? It makes it possible to do some things without even thinking..."
Russell; "It'll be a heated debate for a while... Some things are positive, some negative. There's going to be a reorientation... It has to happen."
Nova; "The danger is that if you delegate thinking [inside education] to a computation service... you may not actually understand enough to know if the answer that comes back is correct."
Russell; "That's a valid concern."
"You rely more on your computational engine than natural language... but you lay a lot of emphasis on the linguistics in your system. So if it's not NLP what is it?"
Russell; "Domain linguistics, mainly; mathematical language, engineering language, etc... We think about how people describe things and search in these domains... and crawl the web looking for examples of how people use language in these domains."
"Stephen is focussed on quality of data, which is important to a lot of people here. There aren't a lot of tools. In addition to making your data store, I wonder if there might be scope to make some of your data curation tools available to the community, to improve the data out there."
Russell; "Great point. Can we make these tools genuinely useful to people, without creating a support nightmare..."