NAME
sta2phrases - This script extracts all aligned phrase pairs from a tree-aligned parallel treebank. The output is written to STDOUT in Moses (phrase extract) format.
SYNOPSIS
sta2phrases alignments.xml
DESCRIPTION
sta2moses
runs through all node alignments and extracts pairs of phrases (yield of source and target language subtree) and prints those phrases in Moses compatible format. These phrases can then be used in phrase-based SMT if you like.
SEE ALSO
Lingua::Align::Trees, Lingua::treealign
AUTHOR
Joerg Tiedemann, <jorg.tiedemann@lingfil.uu.se>
COPYRIGHT AND LICENSE
Copyright (C) 2009 by Joerg Tiedemann
This library is free software; you can redistribute it and/or modify it under the same terms as Perl itself, either Perl version 5.8.8 or, at your option, any later version of Perl 5 you may have available.