Package cc.mallet.fst.semi_supervised

Class Summary

Class	Description
CRFOptimizableByEntropyRegularization	A CRF objective function that is the entropy of the CRF's predictions on unlabeled data.
CRFOptimizableByGE	Optimizable for CRF using Generalized Expectation constraints that consider either a single label or a pair of labels of a linear chain CRF.
CRFTrainerByEntropyRegularization	A CRF trainer that maximizes the log-likelihood plus a weighted entropy regularization term on unlabeled data.
CRFTrainerByGE	Trains a CRF using Generalized Expectation constraints that consider either a single label or a pair of labels of a linear chain CRF.
CRFTrainerByLikelihoodAndGE
EntropyLattice	Runs subsequence constrained forward-backward to compute the entropy of label sequences.
FSTConstraintUtil	Expectation constraint utilities for fst package.
GELattice	Runs the dynamic programming algorithm of [Mann and McCallum 08] for computing the gradient of a Generalized Expectation constraint that considers a single label of a linear chain CRF.
StateLabelMap	Maps states in the lattice to labels.