Thanks for your answers. I need to understand the lexicalized reordering in moses which can change the code later. I have some questions:
One of the intermediate files which is made in model directory is “extract.o.sorted”, that includes reordering examples with its orientation. Why is not discontinues orientation in this file while In the documentation of moses is : there are three orientations for a phrase pair(mono,swap,disc.)? For example, please consider these two samples for a same phrase pair (part of extract.o.sorted file): e1 e2 ||| mono mono ||| f1 f2 e1 e2 ||| other mono ||| f1 f2 What is the meaning of these samples? meanwhile, lexicalized reordering type is msd-fe. On 3/20/11, Philipp Koehn <[email protected]> wrote: > Hi, > > the best way to understand reordering, you have to keep > in mind the alignment to the source. > > If f1, f2, and f3, are the source phrases of the sentence in > that order, and you translate f1->e1, f3->e2, f2->e3, > meaning you first translate f1, then f3, and then f2, then > f1->e1 is consider monotone, > f3->e2 discontinuous (because it has connection to the previous phrase), and > f2->e3 a swap (because it swaps order with the previous phrase). > > The IWSLT paper gives some illustration of it, > I hope this helps. > > -phi > > > >> On 19/03/2011 15:05, Neda NoorMohammadi wrote: >> >> Hi, >> >> The documentation is particularly scarce on lexicalized reordering , >> so I don’t understand the detail! Also, i studied Koehn’s IWSLT paper. >> How is lexicalized reordering in moses? >> >> Whether the reordering in moses just is done on segments of source >> sentence? if so, when a segment for translating is selected, one of >> the hypothesis that is produced is: >> with considering the probability of swap orientation this phrase >> with previous phrase, the translation of this phrase with translation >> of previous phrase in old hypothesis is swapped and is build a new >> hypothesis. A simple sample is: >> >> e1 e2 e3 : old hypothesis >> e4: the translation of new segment >> (e3,e4) --> swap >> e1 e2 e4 e3: new hypothesis >> >> is it correct? >> >> Also, what is subcategory of lexicalized reordering code in moses? >> >> 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 >> >> > > _______________________________________________ > Moses-support mailing list > [email protected] > http://mailman.mit.edu/mailman/listinfo/moses-support > -- NoorMohammadi _______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
