Hi, On Mon, Oct 27, 2008 at 2:20 PM, Joerg Tiedemann <[EMAIL PROTECTED]> wrote: > > I have two questions about Moses: > > (1) I realized that the symmetrization heuristics do not produce the > same result running Moses in different language directions. In > particular, the model/lex.* files are slightly different (different > pairs and also different scores). I expected the lex.e2f to be the same > as the lex.f2e in the other direction but it's not. (but maybe that's > normal). This should also effect the phrase-extraction, shouldn't it? (I > didn't check). Are there any consequences?
This is has to do with the way the heuristic steps through potential new alignment points. Since it is done either line by line or row by row, to does not work exactly the same in the other language direction, since the role of lines and rows is reversed. -phi _______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
