Month: October 2008

Last week I posted about Google’s new “In Quotes” beta. Today Bob Carpenter posted about how to extact quotes using LingPipe. Worth a read.

My colleague Oscar Berg at The Content Economy posted about how the name of his blog is drawing a surprising amount of traffic from people looking for content about the economy:

The last weeks the most commonly used search keywords are:

“what’s the worst that could happen with the economy” and “how does the economy crash effect people as individuals¨ (in slightly different variations) .

The search statistics also show that a lot can be done to improve relevancy in search.

Indeed. We really need to do better when it comes to blog search–and, by extension, search for semistructured content on the web.

Maybe it’s just an accident, but I was surprised to see that the top search result on Google for Avrim Blum is not Avrim’s page, but rather John Langford‘s:

No idea whether this a prank or just an accident.

Thanks to Kristiaan Pelckmans for posting about the upcoming Workshop on Empirical Hypothesis Spaces at NIPS 2008:

This workshop asks for insights how far we may/can push the theoretical boundary of using data in the design of learning machines. Can we express our classification rule in terms of the sample, or do we have to stick to a core assumption of classical statistical learning theory, namely that the hypothesis space is to be defined independent from the sample?

The workshop chairs are an impressive crew: Maria-Florina Balcan, Shai Ben-David, Avrim Blum, Kristiaan Pelckmans, and John Shawe-Taylor.