Slashdot Mirror


Haystack: A More Compelling View Of Your Data

Peristaltic writes "MIT's Haystack project has released the source for it's "Universal Information Client", Haystack. In their words: 'Haystack looks into the use of artificial intelligence techniques for analyzing unstructured information and providing more accurate retrieval.' Unlike some attempts I've seen in the past to pull it all together on my desktop, Haystack shows some promise -- One of it's more useful features allows you to take the information you've been wallowing through, and have Haystack continually refine a 'dynamic hierarchy' until you get what you need. Haystack also performs some neat tricks such as combining Email, IM, web pages, etc. into a single inbox."

1 of 246 comments (clear)

  1. Neat approach to the chaos problem. by Meat+Blaster · · Score: 0, Redundant
    I was looking at this sort of concept about four years ago, but was stymied by issues that were only recently addressed by artifical intelligence. One of the techniques that showed promise is ruminant nomination -- being able to abstract everything to a set of individual but similar (comparable) characteristics is a must. Unfortunately, such an algorithm was nearly uncomputable at the time, and bubblesort just won't cut it.

    What's interesting about Haystack is that it seems to take advantage of such an algorithm, and in such a manner as to permit multiple feeds simultaneously on harvested data. Hopefully, the source is available somewhere to check out, because I'm curious about how they managed it.