Hi, this is indeed not properly supported.
I would suggest to tokenize the input for tuning and testing outside EMS and specify the tokenized files. Just to be clear: Are you talking about XML instructions to Moses as described here: http://www.statmt.org/moses/?n=Moses.AdvancedFeatures#ntoc11 Or are you talking about tags that happen to be in your input and that should be preserved? In that case it is probably better to strip out the tags and re-insert them afterwards into the output with the help of word alignment. -phi On Sun, May 25, 2014 at 12:16 AM, Wei Qiu <[email protected]> wrote: > Hi, > > Is it also reasonable to use xml markup for tuning? > > How can I use xml markup in ems? I am asking because it seems that the > tokenize step would break the xml tags into tokens. > > Thanks in advance. > > Best, > Wei > > _______________________________________________ > 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
