Hi, the factors do not have any real meaning to the translation engines. So if you use POS tags or CCG supertags, you can use the exact same setup.
One comment on your training command: you use factor 0 and 2 in the output, but not factor 1. Maybe you should change this to factor 0 and 1. -phi On Mon, Dec 15, 2014 at 8:27 PM, Eng HAR <[email protected]> wrote: > I'm trying to train a model with CCG supertags for the target (English) > cause my model from Arabic into English . > Actually i found how to deal with POStaggs , but what about CCG supertags ? > What can i change exactly ? > > Thanx alot > > % train-model.perl \ > --root-dir pos \ > --corpus factored-corpus/proj-syndicate.1000 \ > --f de --e en \ > --lm 0:3:factored-corpus/surface.lm:0 \ > --lm 2:3:factored-corpus/pos.lm:0 \ > --translation-factors 0-0,2 \ > --external-bin-dir .../tools > > > -- > رب اعتق رقابنا ورقاب والدينا من النار > > Hamdi Ahmed Rajeh > Hunan University - China > Phd Researcher > 0086-15211108249 > > > _______________________________________________ > Moses-support mailing list > [email protected] > http://mailman.mit.edu/mailman/listinfo/moses-support > _______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
