Hi, maximum entropy is one learning method for log-linear models, and MERT is another one. However, MERT is based on the Powell algorithm and there are no guarantees for convergence.
-phi On Thu, Jan 21, 2010 at 2:38 AM, david li <[email protected]> wrote: > Hi, all > > I'm new here, and I've one question on log-linear models for SMT. > > Since log-linear model is based on MaxEnt principle, it has the nice > property with global optimum. > > However, I remember that during MERT training, one way to avoid local > maximum with log-linear training is to select several starting point > randomly. Then the max value will be chosen. > > Is there anything wrong for me and thanks very much! > > > David > > _______________________________________________ > Mt-list mailing list > > _______________________________________________ Mt-list mailing list
