Hi, you could just handle this in pre- and post-processing.
-phi On Tue, Jul 6, 2010 at 2:12 PM, Raphael Payen <[email protected]> wrote: >> * when decoding you first replace the number with the NUMBER token, and then >> replace its translation NUMBER token with the number in mind. > > For this replacement, I need to keep the value of the number number > along the translation, so the best option seems to add it as a factor > ? Then, all other words of the corpus need to have an empty factor. > It's not such an awful problem, but it seems strange. > > _______________________________________________ > 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
