Hi,

I would like to know where it is recommended to use SimpleTokenizer or
a machine learning based model for tokenizing the input of
NameFinderME models (for English person, place and organization models
for instance).

I suppose it is best to use the same tokenizer as the one used when
training the NameFinder models in the first place, but I did not find
any reference on the model downloading page at:

  http://opennlp.sourceforge.net/models-1.5/

Cheers,

-- 
Olivier
http://twitter.com/ogrisel - http://github.com/ogrisel

Reply via email to