Hi, you do not have to provide these markers in the input, in fact that would be wrong. They are added internally by the decoder for language model scoring.
-phi On Thu, Jun 9, 2011 at 5:53 AM, Tom Hoar <[email protected]> wrote: > Hieu, > > Your most recent SVN update comment says: > "dont process unknown words for 1st or last place. They're the <s> & > </s> and should only be handled by the glue rules" > > We generate language model text corpus files with the <s> and </s> tag on > each line, but we do not add them in 1st/last place. Should they be there? > Is it a problem if they're not there? > > Thanks, > Tom > > _______________________________________________ > 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
