We are using a 23148 sentences bilingual parallel corpus with limited domain of tourist conversation.
What do you mean by uncertainty? How we can test it? does it mean the probabilities of the model have not good distribution to choose the best choice?! Is there any solution?! How about the smoothing problem we point to, really there is no smoothing part for moses reordering models? then what happens if none seen events happens? ُThanks On Thu, Sep 1, 2011 at 2:17 PM, david li <[email protected]> wrote: > Hi, > > Can you describe the amount of training sentences and test set you use? > Or maybe you can make another test for other language pairs. > I guess it is because of the data sparseness and leads to uncertainty > during your experiments. > > > > On Wed, Aug 31, 2011 at 8:00 PM, Neda NoorMohammadi > <[email protected]> wrote: > > Hello all, > > > > We are testing different reordering models in our system ( source > language > > structure is sov and target is svo). > > The results are amazing! The distance based model improves the results in > > compare to lexical reordering models. > > > > we want to know is it true for other pair languages and also: > > Isn't it true that lexical reordering is offered to improve the > reordering > > models? Then why we have get just the reverse?! How we can argument why > it > > has happend to our system? > > > > Also I have checked the LexicalReorderingState.cpp class. There is a > > commented part in the code which shows it has uses no smoothing model for > > estimating none-seen events of this model. Am I right? > > > > Thanks > > > > > > _______________________________________________ > > 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
