If you use the syntax straight out of the parser as-is, i think most
people have found it hurt performance. Non-syntactic phrases are just
too useful so you need to do something in addition to just adding a
parse tree.
On 08/04/2011 11:27, Pratyush Banerjee wrote:
Hi All,
We have been trying to use Syntax Models for Moses for some time now.
We have trained tree-to-tree models and HPB models and were trying to
compare the results with standard PBSMT models.
We use en-de as language pairs and about 1.2 million lines as training
data. For tree to tree models we have used Berkeley Parser for parsing
both languages.
However i found that Tree-to-Tree scores were much lower(about 4 BLEU
points) compared to the PBSMT models. The HPB model (hierarchical
moses without syntax) is slightly better than the PBSMT models.
Is this behaviour normal. I am quite new to syntax based models, hence
the question.
Also do we need to parse the devsets during tuning of the tree-to-tree
models ?
Thanks and regards,
Pratyush Banerjee
_______________________________________________
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
