Looking for Answers in the Age of Search

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."

Real Aquaint Web Site...

[xyzzy]

...is here:

http://www.ic-arda.org/InfoExploit/aquaint/index.h tml [ic-arda.org]

Cluster Searching

[LordMyren]

Google really lacks at filtering out noise. I was looking for Gran Turismo tuning stuff yesterday. Gran Turismo tuning -"release date" -cheats -faq, &c &c &c. The list of restrictions to filter out noise kept getting bigger and bigger, but it was still just the big agencies that were getting hits, nothing about the game itself.

Clusty [clusty.com] on the other hand is no sucker for a press release. I find its much smarter at locating actual content.

Myren

Re:What I'd like to see....

[JonBuck]

What you need to do is find the right search tool.

The Thomas Register might be more what you're looking for.

http://www.thomasnet.com/ [thomasnet.com]

Re:Looking for Answers...

[TuringTest]

Yes, the Semantic Web goals are exactly the idea stated in the article.

Regular Slashdot crew don't get it because of the overly complicated status of the current S.W. standards, but in the future some lightweight implementation of the Semantic Web idea will take off and we will have search engines that somehow "answer questions" instead of just "finding words".

Re:What I'd like to see....

[DeadSea]

You might actually like MSN search [msn.com]. They seem to heavily favor the home page of sites. So much so that MSN will often send a bunch of traffic to the front page, but virtually none directly into sub pages.

I find this behaviour annoying because I tend to search for more obscure stuff. But if you search for company names, this does have the nice effect of almost always getting the companies home page.

We use Mindmeld

[MichaelPenne]

for an 'intelligent' FAQ.

It uses more of a human based system, it 'learns' as folks type in different questions (and versions of the same question)and tell it whether the answers it gives are helpful. As uses 'teach' it, it gets better at providing relevent results to natural language queries.

Worth a look:
http://mindmeld.sourceforge.net/mmsf/index.php [sourceforge.net]

Re:What I'd like to see....

[Mozk]

Experts-Exchange has solutions when you scroll down. I've never had to sign up for anything there.

Re:Looking for Answers...

[TuringTest]

Have you heard of "lowercase semantic web"? Things like del.icio.us, Flicker, Xhtml Friends Network and other open API lightweight services will be the first tools that will spread the idea of easy-to-use, always-available semantic services.

QuASM

[mr. mulder]

I would have to disagree with the poster - significant researching efforts have been put into question answering and factual data retrieval from the web. Visit the University of Massachusetts Center for Intelligent Information Retrieval website [umass.edu]. For a more specific project, check out QuASM [acm.org]