
A part-of-speech tagging model and tag dictionary are included with this project.

The model derives from a combination of GENIA, Penn Treebank (Wall Street Journal) and anonymized
clinical data per Safe Harbor HIPAA guidelines. Prior to model building, the clinical data was 
deidentified for patient names to preserve patient confidentiality. Any person name in the model 
will originate from non-patient data sources.


To build a model of your own, you need to

1) obtain training data - see data/pos/training/README
2) build a model using the training data. 

After you have obtained training data, you can build a model by running the following:

java opennlp.tools.postag.POSTaggerME <training-data> <model-name> <iterations> <cutoff>
where <training-data> is an OpenNLP training data file as described in data/pos/training/README
      <model-name> The file name of the resulting model.  The name should end with either '.txt'
                   (for a plain text model) or '.bin.gz' (for a compressed binary model).  
      <iterations> The iterations argument determines how many training iterations will be 
                   performed.  The default is 100.  
      <cutoff>     The cutoff argument determines the minimum number of times a feature has to be
                   seen to be considered for inclusion in the model.  The default cutoff is 5.  

The arguments <iterations> and <cutoff> are, taken together, optional - i.e. you should provide 
both or provide neither.  
