On January 23-27, 2006 I was at the Institute for Pure and Applied Mathematics, UCLA, California attending a now famous Document Space Workshop. I took some pictures, but did not find these until now.
I’ve posted these in my facebook page, posing with back then IPAM director and with world-recognized LSI expert Dr. Michael Berry and his former students. To learn more about the workshop and the speakers, follow this link http://www.miislita.com/ipam/ipam-document-space-workshop.pdf
Jelinek explained .. He then present examples of
random decision trees and some drawback of these trees.
Interesting, if I am not missing anything, decision trees are the mainstream in the learning-to-rank (see, e.g., the Yahoo challenge). I wonder what exactly he criticized.
makes clear that similarity and disimilarity in terms of
Euclidean space and Euclidean distances is not enough to represent documents and queries.
Well, wasn’t it obvious after invention of BM25 and other language models? š
WOW. That was a long ago and I no longer have the original notes I took. But, you can visit IPAM site (google it) and search for the individual speaker presentations.
I hope that helps.
Thank you! That was a stupid question. The site does have a presentation, even the audio recording.
Yep. That’s one thing I like about IPAM. They make things of easy open access. To stay at the cutting edge of many disciplines, IPAM site is the place to be.
Agree, BTW, FJ presentation on the use of random forests in speech recognition is quite insighful. Especially in the light of common knowledge that generative learning models outputperform discriminative learning models for speach recognition.
Glad you like it! IPAM, and six years later that workshop in particular, was and still is a fest for the inquisitive mind.