Hi, > First, I wonder how I can use the much bigger monolingual corpus for > training the generation step. Where in the config or meta files can I > specify data to be used?
Currently, EMS is not set up to allow this option. I suggest to run one experiment all the way through with only the parallel data as training data for the generation step. Then, carry out the generation step by hand for your large data set, and add the line generation-table = /your/file/location to a copy of the config file, and run experiment.perl with it. -phi _______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
