Hi, please check http://www.statmt.org/moses/?n=FactoredTraining.BuildReorderingModel and the papers referenced in there, especially http://homepages.inf.ed.ac.uk/pkoehn/publications/iwslt05-report.pdf
In short, a line like > and products are ||| 企業界 ||| mono other indicates that the phrase pair (and products are, 企業界) was found in a sentence in the corpus, and in that sentence, it was aligned monotone to the previous and discontinuous to the following phrase pair. -phi On Mon, Apr 30, 2012 at 5:24 AM, Fong Po Po <[email protected]> wrote: > > Dear All: > We can get extract.o after training Moses. > This extract.o like this: > and products are ||| 企業界 ||| mono other > losing ||| 每年 損失 ||| other mono > losing millions ||| 每年 損失 數百萬 ||| other other > ............. > Is this file get from computing the probability of different types of > orientation for phrase pair (e,f ) and the probability of different types of > orientation with > p(orientation|e,f) = (count of orientation in (e,f) ) / (count of all types > of orientation in (e,f) ) > Am I right? Thanks! > If not, how does it know orientation type of > "and products are" and "企業界" is "mono other"? > Thanks! > Best Regards, > Fong Pui Chi > > _______________________________________________ > 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
