Hi, the tree structure in rules are obtained by running a parser over the training data - either on the source side, target side, or both, depending on the type of model you want to use.
Popular English parsers are the Berkeley or Stanford parser. The Berkeley parser also has a Chinese model. -phi On Mon, Dec 3, 2012 at 4:17 AM, kehai chen <[email protected]> wrote: > Hi,all, > > I want to test the string-to-tree model in the english-chinese > language,please How to get the tree rules of Chinese corpus? If you have > this experrment,Could you help me deal with my Chinese corpus?Thanks. > > > > Chen > > _______________________________________________ > 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
