Dear readers, we keep getting strange, unexpected and sometimes illogical results in more than one series of SMT experiments using the JRC Acquis parallel corpus. Often the same methods work fine on Europarl. Our question is -- has anyone else had strange experience with JRC Acquis? I mean, is it us or the corpus?
Thanks in advance, Mark & Heiki University of Tartu _______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
