public void train() throws Exception {
/*
* Read the training dataset into an object which implements DataIter
* interface(trainData). Each of the training instance is encapsulated
* in the object which provides DataSequence interface. The DataIter
* interface returns object of DataSequence (training instance) in
* next() routine.
*/
DataIterImpl trainData = new DataIterImpl();
/*
* Once you have loaded the training dataset, you need to allocate
* objects for the model to be learned. allocmodel() method does that
* allocation.
*/
allocModel();
/*
* You may need to train some of the feature types class. This training
* is needed for features which need to learn from the training data for
* instance dictionary features build generated from the training set.
*/
featureGen.train(trainData);
/*
* Call train routine of the CRF model to train the model using the
* train data. This routine returns the learned weight for the features.
*/
double featureWts[] = crfModel.train(trainData);
/*
* You can store the learned model for later use into disk. For this you
* will have to store features as well as their corresponding weights.
*/
crfModel.write(baseDir + "/learntModels/" + outDir + "/crf");
featureGen.write(baseDir + "/learntModels/" + outDir + "/features");
}
