Hi everybody, as you may know, Moses now also supports hierarchical and syntax-based models: translation models that are based on a context-free grammar formalism and that allow the use of syntactic information at the source and/or target.
The tree-based model and chart decoding code in Moses has been available for a while, but there is now also a tutorial: http://www.statmt.org/moses/?n=Moses.SyntaxTutorial This version is currently available in a side branch, since the merging with recent improvements to the main branch (especially multi-threaded decoding and a feature function overhaul) will take some time. We expect to merge the two code bases over the winter. Both branches are fully functional. Also note that the new uniform training code for syntax-based, hierarchical, and plain phrase-based models has been streamlined an extended and offers, for instance, Good Turing smoothing for better probabilities of low-count phrase pairs. Almost all of the tree-based code was written by Hieu Hoang, who deserves full credit for this. Regards, Philipp Koehn _______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
