You can train a reordering model using train-factored-phrase-model.perl that learns reordering patterns from a parallel corpus. There's also been a lot of work done on doing reordering with hand-written rules that apply before translation so as to make the source language have a structure that is more like the target language. This can be especially helpful when the characteristic word orders of the two languages are quite different (as is the case with English and many Indian languages). See, for example, this paper: http://www.aclweb.org/anthology/N/N09/N09-1028.pdf Good luck, Chris
On Tue, Mar 2, 2010 at 11:20 PM, bharani priya <[email protected]>wrote: > Sir > > Now i am trying to reorder my source language according to target > language.This work is to bring more accuracy in SMT (English to Indian > language) > > If suppose my source language is English and my target language is some > Indian language how can i apply my reordering rules to change my source > to target language. > > Is there any specific rules to do that..? > > How can i proceed this work with moses? > > Can u suggest some ideas regarding this reordering? concept. > ------------------------------ > The INTERNET now has a personality. YOURS! See your Yahoo! > Homepage<http://in.rd.yahoo.com/tagline_yyi_1/*http://in.yahoo.com/> > . > > _______________________________________________ > 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
