Peter Turney now has a blog. Who is Peter? One of the most interesting researcher I ever met. It is not so much that the research he does is different from any other research, but it is the way he does it.
His first post is rather deep, but I was able to follow most of it. He makes us a promise:
I suspect that it may be possible to reduce attributional similarity to relational similarity, and I have started sketching an algorithm for performing this reduction.
Maybe we will learn more about it later?