--- Mark Waser <[EMAIL PROTECTED]> wrote: > >> I could have used a lossy test by using human subjects to judge the > >> equivalence of the reproduced output text, but it seemed like more > >> trouble than it is worth. The lossless test is fair because everyone > >> still has to encode the (incompressible) choice of representation. > > Whether or not the lossless test is fair is irrelevant and you entirely > failed to address my argument that "Requiring an AI to decompress the same > knowledge into a variety of different forms based upon what was input is a > tremendously more difficult problem than AI without that requirement (and > having that requirement doesn't seem to have any benefit)."
The benefit of a lossless test is that you don't need human judges to do a subjective evaluation. I don't believe that it is tremendously more difficult to decompress text exactly than to decompress to different text that has the same meaning. The amount of extra knowledge needed to encode the choice of representations is small. If a sentence can be rewritten in 1000 different ways without changing its meaning, then that only adds 10 bits. As for whether more computation is required, that is debatable. It depends on how you implement the model. Efficient, lossless language models already exist, for example, PPM, distant bigram, and LSA. What model did you have in mind where losslessness would be a hardship? -- Matt Mahoney, [EMAIL PROTECTED] ----- This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=231415&user_secret=fabd7936
