Hi, Philipp I have few questions bellow: 1. What happen if the parallel corpora are decoded with UTF8 format and language model generated by IRSTLM is decode with BIG5? Will it work? 2. If 1. won't work. Do I need to regenerate the language model encoded with UTF8 and rerun the "train-model.perl" script since the language model is replaced with the newer one?
Any suggestion will be appreciated Best regards Moonloki
_______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
