Hi all, I want to use EMS for factored training models on English-to-Turkish translation system. Is there any way to use my own factored corpus because I don't want to write a script that generates factors on Turkish? I hope to be able to indicate my own factored corpus in config file, as such in tokenized corpus, or cleaned corpus. I already have my own tagged corpus consisting of correct representations for all necessary factors.
Any help will be appreciated. Ezgi
_______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
