On Tue, 6 Oct 2009 11:08:28 -0700 (PDT) poifgh <abhinav.pat...@gmail.com> wrote:
> > I have a question about - understanding how are rulesets generated for > ... > a. Is it done manually with people writing regex to see how > efficiently they capture spams? > b. Is there an algorithm that identifies large corpus of spam and the > comes up with these regex'es on its own? > c. Is it a combination of (a), (b)? The optional sought rules are autogenerated, the rest are manual.
