Hi, The en-pos-maxent.bin model is using penn treebank tag set, so I assume the training data set is also from penn treebank ?, if yes, is it WSJ, or Brown ,..?
I have the penn tree bank data set, but with different format from opennlp. If I need to retrain these models, is there utilities to help converting penn format to opennlp format, or I have to do my own conversion ? Thanks.
