Hi, no quick answer, I was planning on taking a closer look at the cube pruning algorithm, but here is a hint: Play with the parameter "-cbp" with values between 500 and 50,000 and you will see a range of different speeds/performances. Be sure to yank up the stack size to something large, several thousand.
-phi On Fri, Feb 20, 2009 at 3:30 AM, zhmmc <[email protected]> wrote: > Dear expert: > Now I find a problem with my new-built moses system.The moses has > provided a new algorithm,cube pruning,to decode.And this new algorithm > speeds up the decoding process.I set the algorithm option of the moses to > cube pruning (stack size :1000)and test it under the linux OS.The result > confirms that cube pruning is faster than the normal beam-search algorithm. > But,when I do the same thing under the WINDOWS OS,set the algorithm to cube > pruning, the complex problem appears: cube pruning works even slower than > the normal beam-search algorithm. I can't find the reason.Can you help me > solve the problem ? I'm eager for your answer Thanks. > > Best Wishes > > Yours > > zhu > hai > > > > ________________________________ > 网易邮箱，中国第一大电子邮件服务商 > _______________________________________________ > Moses-support mailing list > [email protected] > http://mailman.mit.edu/mailman/listinfo/moses-support > >
_______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
