Here's a suggestion: why not try full parsing instead of dependency parsing? maybe the output will be different and easier / more intuitive to transform into what moses is expecting... if not, let me know, I'll be back with something more elaborate
-- Laura Alonso i Alemany FaMAF - UNC Medina Allende S/N - Ciudad Universitaria Córdoba - Argentina http://www.cs.famaf.unc.edu.ar/~laura ø¤º°`°º¤ø,¸¸,ø¤º°`°º¤ø,¸¸,ø¤º°`°º¤ø,¸¸,ø¤º°`°º¤ø,¸¸,ø¤º 2013/6/3 Andrew Vine <[email protected]> > Hi, > > I would like use a dependency tree as input when training.. > > For example.. the dependency tree that I get from freeling for english > looks like this: > > input: What is the time? > > output: > wh-pro/top/(What what WP -) [ > claus/modnorule/(is be VBZ -) [ > sn-chunk/dobj/(time time NN -) [ > DT/det/(the the DT -) > ] > in-brk/ta/(? ? Fit -) > ] > ] > > Previously I passed a shallow parsed tree to freeling. All the tokens were > terminals and so I had no problem converting a shallow based tree to the > xml format stipulated in > http://www.statmt.org/moses/?n=Moses.SyntaxTutorial#ntoc22 > > However how do I send a tree like the one above to moses where tokens are > attached to parent nodes? > > Currently I am using the span attribute.. so I am trying: > > <tree label="wh-pro/top/" span="0-4"><tree label="claus/modnorule/" > span="1-4"><tree label="sn-chunk/dobj/" span="2-3"><tree label="DT/det/" > span="3-3"></tree></tree><tree label="in-brk/ta/" > span="4-4"></tree></tree></tree> What is time the ? > > But I am unsure if this is the way to go.. If anyone has some suggestions > as always It would be much appreciated. > > Regards > Andrew Vine >
_______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
