Slashdot is powered by your submissions, so send in your scoop

 


Forgot your password?
Close
typodupeerror
×
Google Software The Internet

Extracting Meaning From Millions of Pages 138

Posted by kdawson from the data-mining-gone-large dept.
freakshowsam writes "Technology Review has an article on a software engine, developed by researchers at the University of Washington, that pulls together facts by combing through more than 500 million Web pages. TextRunner extracts information from billions of lines of text by analyzing basic relationships between words. 'The significance of TextRunner is that it is scalable because it is unsupervised,' says Peter Norvig, director of research at Google, which donated the database of Web pages that TextRunner analyzes. The prototype still has a fairly simple interface and is not meant for public search so much as to demonstrate the automated extraction of information from 500 million Web pages, says Oren Etzioni, a University of Washington computer scientist leading the project." Try the query "Who has Microsoft acquired?"
This discussion has been archived. No new comments can be posted.

Extracting Meaning From Millions of Pages More

Extracting Meaning From Millions of Pages

Comments Filter:

  • Try the query.... (Score:4, Funny)

    by Finallyjoined!!! ( 1158431 ) on Friday June 12, 2009 @08:49AM (#28306709)
    "Who has dumped Vista?"
    • "How long before TextRunner is slashdotted?"

    • Oh man, it's the new sucks-rules-o-meter for sure. Who hates vista: 55 results. Who loves vista: 11 results. Obviously, vista blows hairy goats. It becomes even more clear when you look at the actual results: somehow "
      Bookmark Islamic Screensaver download-All people (12) love screensaver-Windows Vista Downloads" counts as a hit.. ahh there, a reload with js and the spam disappears leaving 9 :D

    • Why the query

      Who has not been acquired by Microsoft

      doesn't return Yahoo ?
      actually it doesn't return any result ...

    • Re: (Score:2)

      by Nutria ( 679911 )

      Better yet: "Why does Windows suck?"

      Retrieved 0 results for Why does Windows suck?.

      Being in Washington, MSFT has obviously paid them off to filter out unpleasant results.

  • Comment removed (Score:5, Interesting)

    by account_deleted ( 4530225 ) on Friday June 12, 2009 @08:51AM (#28306721)
    Comment removed based on user account deletion
    • Yeah, it's something you'd have to cross-reference, but the main use I see for it is the initial search for information. You ask a question, it gives some answers, then you type them into yahoo or something to look them up/verify what it said. This could be a huge help for things that one may not know a lot about.

      • Wikipedia tried and failed (Score:1)

        by Anonymous Coward

        That is how Wikipedia was meant to be. A group of statements about subjects, all of which can be referenced to some original source. So that people can look up something quickly and then look at the sources for more definite information....

        Seeing how many people cite Wikipedia directly, use it as the main source for their research and the amount of newspapers that have been reported to directly quote inaccurate facts from Wikipedia... I don't think it is working properly. It requires a lot of optimism to be

        • Re:Wikipedia tried and failed (Score:4, Insightful)

          by Colonel Korn ( 1258968 ) on Friday June 12, 2009 @09:50AM (#28307379)

          That is how Wikipedia was meant to be. A group of statements about subjects, all of which can be referenced to some original source. So that people can look up something quickly and then look at the sources for more definite information....

          Seeing how many people cite Wikipedia directly, use it as the main source for their research and the amount of newspapers that have been reported to directly quote inaccurate facts from Wikipedia... I don't think it is working properly. It requires a lot of optimism to believe "People will use that as a initial source and then verify the information"

          That's not wikipedia's failure. Those same people would just be referencing nothing or a web site with zero public review and commenting without it.

    • Re: (Score:3, Insightful)

      by John Hasler ( 414242 )

      The major problem is that it assumes the presence of meaning in Web pages in the first place.

    • Re: (Score:2, Interesting)

      by morgan_greywolf ( 835522 )

      Actually, just like any other search, it just shows ALL of the likely results and you are still responsible for determining for yourself which of the statements is true. It says "CIA killed JFK" but the first result it returns is "Lee Harvey Oswald killed JFK". It also seems to pare down the results somewhat, because I know I've seen conspiracies also suggesting that the KGB killed JFK, or that the Mafia killed JFK. I'm guessing that more people think the CIA killed JFK than the KGB or the Mafia.

    • Re:Not entirely helpful (Score:5, Funny)

      by owlnation ( 858981 ) on Friday June 12, 2009 @09:16AM (#28306991)

      I suppose the major problem with this is that it cannot tell the difference between truth and lies or urban legends, it just repeats what other people have said, even if they are conspiracy theorists. The query "Who killed JFK?" suggests the CIA did it.

      So much like Wikipedia then?

    • shhhh! we aren't supposed to talk about the grassy knoll or the bad men will come again.
    • ... and yet "Who was responsible for the World Trade Centre attacks?" returns no results...

      [/tinfoilhat]
    • Why deal with uncertainties about who-killed-who in the past, when you can have a lot more fun with what could be in the future.
      "Who killed obama?" ... seems an inside job by Hillary is most probable just below a vicious murder by Ted Nugent. Scary!

    • Re: (Score:3, Insightful)

      by jerep ( 794296 )

      it just repeats what other people have said

      I don't see anything new here, most people have done this since the beginning of time.

      • Re: (Score:3, Funny)

        by thedonger ( 1317951 )

        it just repeats what other people have said

        I don't see anything new here, most people have done this since the beginning of time.

        Yeah, Textrunner just repeats what other people have said, like most people since the beginning of time.

    • Re: (Score:3, Interesting)

      by somersault ( 912633 )

      I suppose the major problem with this is that it cannot tell the difference between truth and lies or urban legends

      Most humans can't either, how do you expect a search engine to?

      There will be a lot of false positives and negatives that will be hard to identify as such unless it directly works with something like snopes.com , which kind of defeats the purpose because it means someone has had to research every question anyway.

      If a project like this which simply scoured the whole 'net, you wouldn't really be able to verify anything beyond people's opinions or beliefs, which may or may not be 'true'.

      I think something like t

    • Re:Exactly (Score:2, Funny)

      by bxbaser ( 252102 )

      "The query "Who killed JFK?" suggests the CIA did it"

      Hmmm....And now its not responding because its "slashdotted"

    • Re: (Score:2)

      by knewter ( 62953 )

      And you suggest they didn't?

    • Re: (Score:2, Informative)

      by msbmsb ( 871828 )
      Semantic processing systems like this (it's not something new) aren't usually able to determine correctness. The truth of a statement is assumed and the best these NLP [wikipedia.org] engines can do at the moment is identify conflicts and maybe use some reputation metrics to assign a veracity rating to a particular statement, or notify the user that there are differing conclusions. These systems are just really, like the summary states, "information extraction [wikipedia.org]" systems. Just as a regular search engine will return you the r
      • When humans read, we maintain a running context against which we compare each new sentence. We build a background model and fit knowledge into it, and use it to judge validity of possible interpretations of sentences. I have a problem with systems like TextRunner that purport to extract meaning from single and simple Subject-Verb-Object types of structures. The problem is the lack of broader comparison with existing knowledge and any attempt to reconcile truth and meaning with it. I guess another way of put

  • Nascent AI? (Score:5, Funny)

    by Drakkenmensch ( 1255800 ) on Friday June 12, 2009 @09:02AM (#28306841)
    I've always viewed intelligence as the ability to take unrelated facts and create new and original ideas from their synthesis. This project may very well lead to new ideas to create the first true AI.

    I'll start stockpiling food and armor piercing rounds for the moment Skynet goes live.

    • I've always viewed intelligence as the ability to take unrelated facts and create new and original ideas from their synthesis.

      Intelligence, like insanity, is finding links between seemingly unrelated facts. It can also be keen observation and recognition of interactions between things where others see chaos. Either way, truly unrelated things are just that: unrelated.

      • I should add that the distinction between intelligence and insanity blurs as the relationship between the facts becomes weaker. Well, at least to the observer of the intelligent/insane person.
    • It's easy to create new and original ideas. A random generator can do that. What is difficult is selecting the valuable ones.

      I generally view intelligence as the ability to detect and recognize patterns. If you are good at exact patterns, that is math/logic/science. If you are good at general patterns, then we are talking art/creativity/language.

      Computers have ALWAYS been good at recognizing exact patterns. But they generally need a human to first detect the pattern. They have never been good at re

  • 500 million web pages can't be wrong (Score:5, Funny)

    by Dunbal ( 464142 ) on Friday June 12, 2009 @09:06AM (#28306885)

    Yet strangely, I get a result of:

    TextRunner took 9 seconds.
    Retrieved 0 results for what is the airspeed velocity of an unladen swallow?.

    Meh, call me when this stuff can answer the really USEFUL questions in life.

    • Simply because grepping 500 million pages is slow.

    • Re: (Score:3, Funny)

      by JDHannan ( 786636 )
      And even worse:

      Retrieved 0 results for what is the answer to life, the universe and everything?.
    • Yep. I concur - it couldn't even tell me what the number 42 was used for!

    • Re:500 million web pages can't be wrong (Score:5, Funny)

      by sukotto ( 122876 ) on Friday June 12, 2009 @09:29AM (#28307133)

      Obviously it's not indexing http://www.style.org/unladenswallow/ [style.org]

      estimate that the average cruising airspeed velocity of an unladen European Swallow is roughly 11 meters per second, or 24 miles an hour.

      • meters per second or miles per hour? what? (Score:1, Interesting)

        by Anonymous Coward

        I would go with...

        • ...meters per second and kilometers per hour
        • ...feet per second and miles per hour
        • ...feet per second and meters per second
        • ...miles per hour and kilometers per hour

        But meters per second and miles per hour? WHY?!

        • They wanted a metric measure and a standard measure. Meters per second is a reasonable metric measure for something slow(er than a car), and miles per hour... is basically the only speed measure that Americans understand. (No flaming, I'm American).

        • Re: (Score:2)

          by sukotto ( 122876 )

          It's in reference to Monty Python... you're lucky it was comprehensible at all.

          and now for something completely different...

    • Well, at least you got 0 results. With "where is New York" I got -1 result!

      • Does that mean it sucked the knowledge out of your head? Rather that give a 0 or a positive that would add more knowledge?

    • Just found out: If you just type "airspeed velocity", you'll get as first two results:

      airspeed velocity of an unladen swallow is roughly 11 meters (10), 24 miles (9), 10 meters (2)
      average cruising airspeed velocity of an unladen European Swallow is 24 mph (2)

      It seems to have trouble understanding units, but otherwise the information is found.

    • Try: "where is the colleseum"

  • Zero results (Score:3, Interesting)

    by John Hasler ( 414242 ) on Friday June 12, 2009 @09:12AM (#28306945) Homepage

    I tried half a dozen queries of the sort I often use Google for (example: "What is the velocity of sound in hydraulic fluid?"). No answers.

  • Concise (Score:2, Interesting)

    by moogsynth ( 1264404 )
    Try "Who paid SCO?" Concise, to the point. Nice.

  • Towards a web with only one page: Google (Score:1, Insightful)

    by Anonymous Coward

    Are we moving towards a web in which Google centralises everything on their own pages? These new engines present content without the need to visit pages it originates from. Is Google basically mooching off other people's websites with hardly anything - if anything at all - in return?

    It could be dangerous if the only visitor a web site can expect is the Google bot.

  • But AOL is nothing like Shakespeare.

  • what causes cancer? (Score:5, Funny)

    by umundane ( 1490741 ) on Friday June 12, 2009 @09:38AM (#28307231)

    I learned that

    > smoking (387) causes cancer.

    I was also surprised to learn that

    > girls and women (11) cause most cases of cervical cancer

    This is a great resource if you need to cite a reference for a Wikipedia article.

  • TextRunner confirms it: (Score:5, Funny)

    by guruevi ( 827432 ) on Friday June 12, 2009 @09:39AM (#28307247)

    Who is at Area 51
    aliens (3), Carter (2), Colonel Sanders (2), Hi Group (2) is at Area 51

    Who bombed WTC
    Al Qaeda (5), Bush (5), Clinton (2), 4 more... bombed the WTC

    Who built the pyramids (example on site):
    Egyptians (298), aliens (73), Pharaohs (40), 77 more... built the pyramids

    What contains antioxidants (example on site):
    Coffee (17), Recent scientific research (15), food (6), 5 more... contain significant amounts of antioxidants

    -- man, I gotta get me some more recent scientific research.

  • Slashdot isn't
    a professional news site
    a normal news site
    a social news site
    a News Site
    a valid source
    a reputable source
    the right source
    a healthy online community
    a goddamn online community
    a Terrorist Organization

    • Ah, but look at what Slashdot is:

      Slashdot is the single most important english site (8), another extremely sophisticated example (4), another online community (3), 15 more...

  • I tried asking the real name of Doctor Who, and the site basically crapped out LOL, totally useless.
  • I typed in "how does a computer become self aware?" it just said something about it being busy because it's currently controlling california!

  • "Who is your daddy?" got 0 results.

  • The significance of TextRunner is that it is scalable because it is unsupervised.

    That's what they said about SkyNet.

  • Apparently Mount Marcy, Mount Elbrus, Mount Kilimanjaro and Mount Etna are all the highest mountain. Then again, I was also informed that "high mountains are the hum of human cities torture", so I think I'll just steer clear of mountains altogether.

  • Try
    "What is Slasdot?"

    Answer
    Digg is Slashdot

  • Retrieved 0 results for what is the answer to life, the universe and everything.

    FAIL!

    • Re: (Score:2)

      by nigham ( 792777 )
      That needs a much bigger computer, IIRC. Roughly the size and complexity of Earth, its ecosystem and its organisms.
  • Turns out to be way cooler than Wolfram Alpha. Now just think if it has the whole web. Wait, scratch that, I bet wikipedia's already in there. Also, skynet.

  • Correction.... (Score:5, Insightful)

    by wowbagger ( 69688 ) on Friday June 12, 2009 @10:32AM (#28307983) Homepage Journal

    "...that pulls together facts by combing through more than 500 million Web pages."

    Correction:

    "...that pulls together assertions by combing through more than 500 million Web pages."

    Whether those assertions are correct or even reasonable is a completely different issue.

    It might be interesting to then take those assertions and have some means to validate or invalidate them, but currently that's going to require meat, not metal.

    Now, if you could come up with some form of AI^Walgorithm to do that automatically, then you would have something.

    • Re: (Score:2)

      by ignavus ( 213578 )

      Correction:

      "...that pulls together assertions by combing through more than 500 million Web pages."

      I suspects it just pulls together *sentences*.

  • So I take it this thing also hates grammar?

  • love (53), song (19), Life (16), 81 more... is the meaning of life

    1) of the 81 more, 42 doesnt show up anywhere
    2) the stupid javascript hiding makes copy and paste a pain

  • same fuckers(2) that Framed Roger Rabbit

  • ==> CIA (26), Lee Harvey Oswald (18), Castro (13)

    I knew it...

  • TextRunner gets rid of that manual labor. A user can enter, for example, "kills bacteria," and the engine will come up with of pages that offer the insights that "chlorine kills bacteria" or "ultraviolet light kills bacteria" or "heat kills bacteria"--results called "triples"--and provide ways to preview the text and then visit the Web page that it comes from.

    Wow, incredible. Because doing a search of "kills bacteria" with the quotes on Google won't get you those kind of results. Oh wait, yeah it will.

    • Query: What kills Microsoft:

      First in the list: Linux, Sony, Apple
      Other notable: Steve Jobs

      • Query: What kills Linux

        On the list, Microsoft, Dell, Apple
        And... Steve Jobs.

        • This Steve Jobs sounded pretty good killer, so I did a query:
          What kills Steve Jobs, the result was:

          Retrieved 0 results for what kills Steve Jobs.

    • Re: (Score:3, Interesting)

      by rm999 ( 775449 )

      I think you're missing the point. This is an AI project - it's research. Presumably, the questions you are typing in haven't been processed by a complicated nest of if-thens written by someone who knows English; instead, statistical models of language and meaning were extracted from the internet. Some people claim this is the equivalent of "teaching" a computer.

      The first example, which is what most search engines do, leads to impressive search results but is limited by the logic people can code up. This AI,

  • This has to be played with to be appreciated. On request, it delivered a set of interesting papers about US-EPA misrepresentation of science. And, it returned a nul result for "Has any climate model been validated?"

    This is going to be fun

  • I asked "Where in the world is Carmen San Diego?". The page trhew up a Java error.

    I guess nobody really knows.

  • ... you extract millions from the meaning of pages! ;)

    Sorry, couldn't resist.

  • produces 0 results :P

  • Retrieved 1 result for does god exist. God DOES exist last night (2).

    Well, that answers that question.

  • 'The significance of TextRunner is that it is scalable because it is unsupervised,' says Peter Norvig, director of research at Google,

    I really wondered what he was getting at with this. It seems almost nonsensical, like something someone in marketing would come up with.

    Now that the site is slashdotted I know that he means if only a few people use it, it's very scalable, but if a bunch of people are directed to use it (say, through Slashdot) then it doesn't scale very well.

    • Re: (Score:2)

      by Virak ( 897071 )

      There's nothing nonsensical about it. Just because you don't know what an unsupervised learning algorithm is doesn't mean it's just a random string of words he threw together to sound fancy.

  • Entering the query "Who is George Bush?" returned the following tidbits among other things:

    General Draper was George Bush's guru
    Hurricane Katrina is George Bush's Monica Lewinsky
    Tony Blair is George Bush's poodle
    democratic Iraq is George Bush's formidable legacy
    Iraq is George Bush's waterloo
    Hillary is the democratic version of good old George W. Bush
    blue socks are Critics of George W. Bush
    Bruce Bartlett is George W. Bush Bankrupted America
    biggest terrorist is George W. Bush

Slashdot Top Deals

What is research but a blind date with knowledge? -- Will Harvey

Close