Hi, you have to give a bit more information about your experiment here. You can run the phrase extraction step in isolation to see what went wrong. Are all the input files produced correctly (corpus, alignment and lexical translation files)? What is reported on STDOUT and STDERR when you run the phrase extraction step?
-phi On Mon, Mar 4, 2013 at 3:05 PM, Nikhila Achukatla <[email protected]> wrote: > Hello, > I'm trying to run Moses using the data provided in Moses website. > While training translation system, 3 files namely: > 1 .Phrase-table.gz > 2. extract.sorted.gz > 3. extract.inv.sorted.gz > are created with size of 20B each. But when I extract them they are just 0B. > I don't find any errors while training. > please give me some suggestions regarding this issue as early as possible. > > Thanks in advance > > _______________________________________________ > 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
