edu.nyu.jet.chunk

Class LBFGSTrainer

java.lang.Object

edu.nyu.jet.chunk.GISTrainer

edu.nyu.jet.chunk.LBFGSTrainer

public class LBFGSTrainer
extends GISTrainer

Train an L2 regularized MaxEnt model with the L-BFGS algorithm

Version:

1.0

Author:

yhe

Constructor Summary

Constructors

Constructor and Description
LBFGSTrainer() Create LBFGS trainer
LBFGSTrainer(double c) Create LBFGS trainer with regularization parameter c

Method Summary

Methods

Modifier and Type	Method and Description
opennlp.maxent.GISModel	trainModel(int iterations, opennlp.model.DataIndexer di, opennlp.model.Prior modelPrior, int cutoff) Train a model using the GIS algorithm.

Methods inherited from class edu.nyu.jet.chunk.GISTrainer

setGaussianSigma, setSmoothing, setSmoothingObservation, trainModel, trainModel

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

LBFGSTrainer

public LBFGSTrainer()

Create LBFGS trainer

LBFGSTrainer

public LBFGSTrainer(double c)

Create LBFGS trainer with regularization parameter c

Method Detail

trainModel

public opennlp.maxent.GISModel trainModel(int iterations,
                                 opennlp.model.DataIndexer di,
                                 opennlp.model.Prior modelPrior,
                                 int cutoff)

Train a model using the GIS algorithm.

Overrides:

trainModel in class GISTrainer

Parameters:

iterations - The number of GIS iterations to perform.

di - The data indexer used to compress events in memory.

modelPrior - The prior distribution used to train this model.

Returns:

The newly trained model, which can be used immediately or saved to disk using an opennlp.maxent.io.GISModelWriter object.