Hi Yaqin,

although the name suggests otherwise, the parse-de-berkeley.perl wrapper script 
works fine with the Berkeley parser's English grammar.

I'd recommend passing the -penn option to tokenizer.perl and detokenizer.perl 
on the English side of your data so that the tokenization more closely matches 
the Penn Treebank-style tokenization that the Berkeley parser expects.

Phil

On 12 Nov 2013, at 20:25, Yaqin Yang <[email protected]> wrote:

> Dear all,
> 
> I try to run the tree-based model on chinese-to-english corpus. It seems the 
> default parser in the tree-based model is collins parser. 
> 
> Is it possible to use berkeley parser instead? Does moses have the wrapper 
> for English berkeley parsing results?
> 
> Thanks!
> Yaqin
> _______________________________________________
> 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

Reply via email to