Hi, in all likelihood this is the result of noisy characters that are not visible but are treated as tokens.
-phi On Fri, Apr 16, 2010 at 8:57 AM, Thu, Vuong Hoai <[email protected]> wrote: > Hi Hieu, > > When I read carefully output from training model, I determined that in > lexical file (e2f and f2e) have some lines with wrong format - true > format contains 3 part <word> <word> <prob> and wrong format has only > two part <word> <prob>. Could you please give me some information about > this error? Thank you! > > -- > Thu. > > _______________________________________________ > 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
