I had the exact same experience going from v0.9 to v2.11 a few months ago and after looking into it for several weeks, came to believe the binary table representation was broken in the transition from a global to a per-thread cache. The compact phrase table representation doesn't have the same problems, and switching to it improved performance back nearly to my previous speeds with v0.9.
mike. On 25/09/14 11:48, Mohammad Mahdi Mahsuli wrote: > I was using Moses v0.9 for a long time, and I recently decided to opt > to use the latest version (v2.1.1). In the test time, when loading the > plain models into Moses, there is no difficulty. But when I want to > use the binarized models, the translation time is much more than when > I used the binary models on the old version of Moses.
_______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
