Dear All, I try to train IRSTLM in Arabic news data but when I test it with two words it give me the same probability. I want to know where is the problem ? and if it must to make each sentence in one line because I put whole articles in the same file to build the model.
thank you, Fatma El-Zahraa El -Taher Teaching Assistant at Computer & System department Faculty of Engineering, Azhar University Email : [email protected] mobile: +201141600434
_______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
