Hello, I am using Moses to translate arabic to english and I used french language as my tokenizer for arabic but now I am wondering, how would the system be accurate to any degree if the English is subject-verb-object (SVO) while Arabic is VSO? I thought of using any of the VSO languages available in Moses to be the closest to Arabic but they are SVO? How do you deal with this as I know that Moses depends on as many rules as possible to make it automated to translate even languages that you do not understand? Best regards, Heidi Heweidy.
_______________________________________________ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
