Subject: Re: Semantically Unpredictable Sentences From: =?X-UNKNOWN?Q?T=F3th_L=E1szl=F3?= <tothl(at)INF.U-SZEGED.HU> Date: Tue, 21 Jan 2003 10:15:15 +0100On Tue, 21 Jan 2003, Brent Edwards wrote: > Isn't he referring to sentences that consist of words with low (no) > predictability using only semantic information? > Sure. But how can he formalize "semantic unpredictability"? I mean, the notion of "statistical unpredictability" is well-defined by formulas like entropy, perplexity and such. But how can one state that the sentences he generates are semantically unpredictable? According to what measure? Laszlo Toth Hungarian Academy of Sciences * Research Group on Artificial Intelligence * "Failure only begins e-mail: tothl(at)inf.u-szeged.hu * when you stop trying" http://www.inf.u-szeged.hu/~tothl *