Add True Knowledge’s semantic answer engine to your website

April 13, 2009 | Anthony Ha | Comments |

True Knowledge, which uses natural language processing to understand and answer complex factual questions, is one of the coolest websites I’ve seen in a while. The answer engine is still locked up in a private beta test, but now third-party developers can add the service to their websites and applications.

Perhaps the best way to illustrate True Knowledge’s potential is with a couple of sample queries — about me, of course. When founder and chief executive William Tunstall-Pedoe demonstrated the system, he created an “Anthony Ha” object and filled in some basic information, so now it’s possible to ask questions like, “Is Anthony Ha older than Britney Spears?” (no) and “Does Anthony Ha live in the United States?” (yes).

These aren’t questions you could ask of, say, Google since there’s no web page that spells out the answers. Those answers aren’t stored explicitly in True Knowledge’s database, either, but the system is able to translate my question into natural language units that it can understand, and then to calculate the answer from its existing knowledge. Thus, it knows my birth date, Britney Spears’ birth date, and that my birth date comes after hers. It also knows that I live in San Francisco, and that San Francisco is is in the United States, so it knows I live in the United States. (This kind of inference is also illustrated in the diagram below.)

This sounds similar to what’s promised by the Wolfram Alpha project, but Tunstall-Pedoe says True Knowledge’s advantages include language independence and including the full ontology (i.e., relationships) around each object. Plus, while Wolfram Alpha remains highly secretive, thousands of beta testers have had a chance to play with True Knowledge — not only am I impressed, but so was then-VentureBeat writer Chris Morrison when he tried it out last year and declared it “Cooler than Cuil,” referring to the purported Google-killing search engine. (Chris’ article also has a more detailed breakdown of how True Knowledge compares to some of the other semantic search companies out there.)

The Cambridge, UK company says it builds its database algorithmically with information from Wikipedia, and also from an input system that allows users to not only enter facts but also agree or disagree with those entered by others, thus making it more likely that True Knowledge will provide the right answer. The company says it now has 4.5 million objects (such as “Anthony Ha” or “January 6, 1983″), which have been assembled into 130 million facts (basically relationships between the objects, such as “Anthony Ha was born on January 6, 1983.”)

As for the business plan, the Tunstall-Pedoe says he wants to partner with other companies so they can offer True Knowledge’s answer services. Releasing two application programming interfaces (APIs) is a step in that direction. It will allow developers to start adding the service to their own products for free. There’s a Direct Answer API, which provides a single answer to each question, and a Query API, which accesses the knowledge database directly.

The company has raised $5.4 million in venture funding. It won’t say when the site is opening to the public, but since it’s releasing APIs, that time probably isn’t be too far off.

Next Story: Qik to cut mobile costs for globe-trotters
Previous Story: Roundup: Amazon’s ‘ham-fisted’ error, Facebook’s baseball surge and more

Bookmark and Share

Tags: ,

Photo of Anthony Ha

About the Author, Anthony Ha

Anthony is VentureBeat's assistant editor, as well as its reporter on enterprise technology, cloud computing, and tech policy. Before joining VentureBeat in 2008, Anthony worked at the Hollister Free Lance, where he won awards from the California Newspaper Publishers Association for breaking news coverage and writing. He attended Stanford University and now lives in San Francisco. Reach him at anthony@venturebeat.com. You can also follow Anthony on Twitter.

  • With all due respect to all involved the description of the technology on the website, if remotely accurate at all, describes something that can't deliver anything interesting. There are sound theoretical reasons to believe this and a lot of companies that have walked the same path. It is perhaps hard to discern if one is not familiar with this kind of technology.

    I hate to be a wet blanket, but this is a "me too" company flogging a long-dead horse. Unless there are some mad theoretical mathematics skills not in immediate evidence, this is a dead end.
  • Do you have any specific examples? Did you feel the same way about Wolfram Alpha?
  • Actually yes, I did feel the same way about Wolfram Alpha because there was nothing presented that had not been done before (and A New Kind of Science was grossly oversold as well). A lot of prior implementations of the same thing are obscure, but unless Wolfram has a magic computer science rabbit in their hat, it won't do anything interesting. Indeed, if they had solved enough computer science to do it properly, there are other more interesting applications that are provably equivalent that could be pursued.

    The irony is that this is a repeat of history where inveterate salesmen are selling dead technology to people who do not remember the failure to deliver at great cost to reputation the last time it was sold decades ago. Very few people are actually doing interesting work in this space, and most who are well-known are rehashing old tech. Ask Barney Pell how that worked out.

    But more specifically, semantic search technologies that work the way most people imagine they should are demonstrably impossible without someone solving a theoretical computer science problem or two. No one is claiming these problems have been solved, and so it is reasonable to presume that it is yet another case of someone who does not really understand the theoretical problem overselling their imagined solution. When I evaluate the technology of various startups with fancy software technology, the question I always ask is why it *must* work. In computer science, that is a question you should be able to answer if you understand the technology. It would be great if a company indicated they had solved these problems, but doing so would make lame semantic apps seem like chump change relative to the other applications of the exact same computer science.

    And that is why I am not sanguine. I have seen this pattern so many times in this space that I have lost count. There are many companies claiming to have solutions that our best theoretical computer science says should not be possible unless they are sitting on an epic theoretical breakthrough and forgot to mention it. Considering how many such companies have come and gone (several dozen at least) it is reasonable to be dubious in the absence of other evidence. Maybe Wolfram has something fabulous to offer, but I am not holding my breath.
  • Beth
    Can you explain what you mean by "anything interesting"?

    I'm willing to believe that solving the problem of answering any natural language question on any topic is too ambitious, but you need to think pragmatically here. Lots of things unsuited to keyword search can be achieved by semantic apps without hitting major theoretical obstacles.
  • hvk
    "demonstrably impossible without someone solving a theoretical computer science problem or two"

    could you piont us to these theoretical problems?
  • I disagree that nothing "interesting" can be done by services like True Knowledge and Wolfram Alpha.

    Neither company claims to have solved a new computer science problem. They are simply applying existing techniques in better ways. In the case of True Knowledge they are crowdsourcing a database of facts that they can then reason against. Reasoning does work, if the facts are sound. The key is to curate the facts well. Their community-based fact curation system solves that. That is what they have innovated. It makes it easy to scale a vast knowledgebase of facts via a crowdsourced approach, thereby breaking the barrier of what one company could possibly data-enter on their own. In theory they should be able to gather more facts than Wolfram Alpha, faster.

    On the other hand Wolfram Alpha has put a lot more work into the depth of problem-solving their system can perform. They can do calculations that are far beyond the capabilities of True Knowledge. They are not openly crowdsourcing their knowledgebase, but instead have a team of curators working diligently to suck the data in from other datasets automatically -- which is effectively curated crowdsourcing via third-party datasets. The tremendous computational abilities of Mathematica plus web-scale data to compute against is significant and new. And interesting to some people -- namely anyone who wants quick answers to science or math questions for example.

    Both of these companies have potential business opportunities. There is nothing provably impossible about what they are CLAIMING to solve. They are not claiming to have revolutionized computer science. I view both companies as really focused on more efficient solutions to existing problems, rather than radically new solutions.

    In any case, what is "interesting" to a computer scientist (which Andrew, above, sounds like he may be) is probably totally irrelevant to consumers on the Web, and vice-versa.
  • "In any case, what is 'interesting' to a computer scientist (which Andrew, above, sounds like he may be) is probably totally irrelevant to consumers on the Web, and vice-versa."

    Ha! Good point.
  • Thanks Nova. I'm a computer scientist. I'm also a loss what these unbreakable "theoretical computer science" laws actually are. A lot of what we are doing is extremely difficult (to put it mildly) and many people have regarded it as too difficult to attempt, but we have proven it is possible - and with good engineering and persistence rather than by solving unsolvable math problems.

    Having said that I'm also quite used to being told that True Knowledge is doing something theoretically impossible. In fact this is the third time in the last two weeks that someone has told me that.

    The bottom line though is that True Knowledge provably does work. We still have lots more to do but are answering real world questions, correctly and in volume and have solid data to prove this:

    http://blog.trueknowledge.com/2009/03/true-know...

    We've also had thousands of people try the technology and now also have an open API that anyone can use in their own applications.
  • Very interesting discussion here: we are developing semantic technology (and applying it to search engines and many other applications) from much before the current hype about Semantic Web so probably I could add one thing or two on this topic.
    Said that being cooler than Cuil is probably the easiest thing in the world :-) and that a real judgment about this new service will be possible only when it will available for testing (the same is true for Wolfram Alpha), I think that there is some truth in all the comments.

    For the everyday people, a semantic Q&A system is something magical where you can ask any type of question and, in a fraction of time, receive a precise answer: if we reason in these terms (and a lot of hype and wrong expectations from many companies in the past made people think so), Andrew is right as there are fundamental and very complex problems that are far to be solved (and I don't think that Wolfram solved it while William was very honest in his description) and probably will never be solved.
    But if we move our point of view to the delivery of a useful Q&A service that can answer with a good quality a big set of common and frequent questions for Web users, this is doable: it requires a lot of work (and money), a very good technology (and I think it can be language independent only partially) and a strong, strong commitment (as Edison said, genius is one percent inspiration and ninety-nine percent perspiration).

    It will not be a Google killer (or even a real competitor) but it could be a very good complement for specific fields and needs: as it is very expensive to develop such a system that can be really useful in everyday life (without big investments, you risk to be marginal as you can answer only a fraction of the most common questions), it seems that Wolfram Alpha has better chances (from the number of people involved, they have probably invested something like $10 to $15 million up to now) but I don't see any need of something like Mathematica that seems more a limit than an advantage as it increase by an order of magnitude or two the number of servers needed to deliver the service (from what I read, I would not be surprised if Wolfram decided to use it only to demonstrate how powerful it is even in contexts where it is not needed).

    I will be happy to add something more specific in the moment I can test the two systems with real questions (and answers) and check if they deliver what they promise.
  • Beth
    Marco, have you signed up for a True Knowledge beta account yet?
  • No, I normally prefer to wait for the version 1.0 to test something that is more solid: if it will take too much time, maybe I will change my mind.