Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!

 



Forgot your password?
typodupeerror
×
The Internet Data Storage IT News

Looking for Answers in the Age of Search 95

prostoalex writes "James Fallows, in a New York Times article, notices that search engines are getting pretty good at providing information for simple keyword-based queries. However, when it comes to the actual information, such as finding the necessary data and statistics, they're not doing a great job. The article talks about the NSA- and CIA-sponsored Aquaint project that aims to deliver answers to questions that might be expressed with a variety of keywords, and need to be 'understood' by the search engine before providing the answer."
This discussion has been archived. No new comments can be posted.

Looking for Answers in the Age of Search

Comments Filter:
  • by Chowser ( 888973 ) on Sunday June 12, 2005 @06:59PM (#12797942)
    One thing missed in so many search engines now is finding information on a particular company quickly and efficiently. Often when I type a particular company into google or another search, I get a bunch of other hits before the actual company itself. Now, bigger companies come as the first hit often (i.e., apple, dell, canon, etc.) Try finding for that lesser-known company though and you'll encounter a lot of crap first. The company listing should always come first.
  • by oneiros27 ( 46144 ) on Sunday June 12, 2005 @07:27PM (#12798085) Homepage
    Than finding 50+ people asking the same question you are, and not a single answer. (or even only one person asking the question, but because the mailing list or newsgroup was being archived on more than one website, you find the same question over and over again).

    It's even more annoying when you had the same question a couple of months before, and had found the answer, but can't remember what the answer was, where your found the answer, or what search terms you had used. (and it's even worse if that site has gone down in its rankings, and something else with people asking the question, but no answer, now ranked higher).
  • by suitepotato ( 863945 ) on Sunday June 12, 2005 @07:59PM (#12798258)
    Can you say Dogpile?

    Google is the number one search agent for me as more often than not with a short list of carefully chosen starting terms, and a little refinement from sleuthing, I can find what I need pretty quickly.

    Do the search engines have to be so smart they find what we meant to find or even what we think we meant to find as opposed to what we literally asked for? They're tools, like library cards, not servants there to do our work for us and stop us from thinking about the search process. Are we complaining because this all isn't as brainless as AOL?
  • by SkiifGeek ( 702936 ) <info@nOspAM.beskerming.com> on Sunday June 12, 2005 @08:00PM (#12798260) Homepage Journal

    I think that there will always be a need for knowledge specialists (professional researchers), whose job it is to develop useful results from requests for information, using whatever tools are at hand.

    Tools like Google and MSN Search are not the only thing you need to find information. There are still places for other information, and 'because Google said so' is not a valid reason for accepting information as relevant, or factual.

    Although these tools will continue to improve, the application of wisdom will still require human input to make the results useful.

  • by drgonzo59 ( 747139 ) on Sunday June 12, 2005 @09:18PM (#12798766)
    These sort of things always reduce to the problem or natural language processing and recognition. The question that is really asked is "Can computers understand human language and act accordingly?" that is not new and it has been the topic of research for decades. To answer a natural language query, the system has to have common sense among other things (stuff that everyone of us knows and we know that others know it). When we ask the computer a question most of the time we assume the computer has the same common knowledge that we have and that is a problem.

    It is better to teach people instead to use the existing search and teach them a small query language (think of Google's link: define: site: modifiers) than to teach the computer human language (we certainly don't want it to because it might become aware of itself and see us humans for who we are, then it will either want to destroy us or destroy itself out of frustration ;)

  • by Anonymous Coward on Monday June 13, 2005 @03:06AM (#12800555)
    To answer a natural language query, the system has to have common sense among other things (stuff that everyone of us knows and we know that others know it).

    The computer only has to appear to have common sense; it doesn't actually have to have common sense. This is the key to how many Aquaint systems work.

    The great thing about the web is that there are billions of web pages out there, many of them created by humans, and many of those humans have common sense. If you're looking for an answer, there's a decent chance that someone has already answered your question (and has written the answer in English text). All you have to do is find that answer string.

    Here is a good example. Suppose I ask the question, "Why have the approval ratings of the US Congress fallen?" I consider this a fairly advanced question, requiring some knowledge of government structure and current events to answer. However, if there is a sentence out in the web that says "Approval ratings of the US Congress have fallen in recent weeks because of gridlock over judicial nominations," all that common sense work has already been done for me. I just need to find that sentence.

Understanding is always the understanding of a smaller problem in relation to a bigger problem. -- P.D. Ouspensky

Working...