2011/4/10 Jörn Kottmann <[email protected]>: > On 4/10/11 10:52 AM, Olivier Grisel wrote: >> >> Ok then let me be more specific: >> >> Has en-ner-{person,place,organization}.bin been trained with the >> output of SimpleTokenizer class or with TokenizerME + en-token.bin? > > I didn't tokenize the training data myself, but it has been tokenized > with some kind of character class tokenizer like the Simple Tokenizer. > > You should definitely use the Simple Tokenizer for the English Name Finder > models.
Thanks you very much. -- Olivier http://twitter.com/ogrisel - http://github.com/ogrisel
