Dear moses-support, when using translation-steps (e.g.): lemma -> lemma(1) pos -> lemma(2) morph -> pos
and generation-steps: lemma, pos -> surface which lemmas are combined with the pos to generate the surface form? lemma(1) AND lemma(2) or just one of them? If it's just one, what happens to the other? Best regards, Christine de Bond _______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
