Hi, I have another question, while manually loading some trained models I get a std::bad_alloc exception. I can usually solve this by binarization.
Why do I *not* get the same exception when tuning the same model with MERT? Regards, Michal Krajňanský
_______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
