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
