Package opennlp.tools.ml.perceptron

Klasse SimplePerceptronSequenceTrainer

java.lang.Object

opennlp.tools.ml.AbstractTrainer

opennlp.tools.ml.AbstractEventModelSequenceTrainer

opennlp.tools.ml.perceptron.SimplePerceptronSequenceTrainer

Alle implementierten Schnittstellen:

Trainer, EventModelSequenceTrainer<Event>

public class SimplePerceptronSequenceTrainer
extends AbstractEventModelSequenceTrainer

Trains models with sequences using the perceptron algorithm.

Each outcome is represented as a binary perceptron classifier. This supports standard (integer) weighting as well average weighting.

Sequence information is used in a simplified was to that described in: Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with the Perceptron Algorithm. Michael Collins, EMNLP 2002.

Specifically only updates are applied to tokens which were incorrectly tagged by a sequence tagger rather than to all feature across the sequence which differ from the training sequence.

Siehe auch:

• PerceptronModel
• AbstractEventModelSequenceTrainer

Feldübersicht

Felder

Modifizierer und Typ	Feld	Beschreibung
static final String	PERCEPTRON_SEQUENCE_VALUE

Von Schnittstelle geerbte Felder opennlp.tools.ml.EventModelSequenceTrainer

SEQUENCE_VALUE

Konstruktorübersicht

Konstruktoren

Konstruktor	Beschreibung
SimplePerceptronSequenceTrainer()	Instantiates a SimplePerceptronSequenceTrainer with a default configuration of training parameters.

Methodenübersicht

Modifizierer und Typ	Methode	Beschreibung
AbstractModel	doTrain(SequenceStream<Event> events)
void	nextIteration(int iteration)
AbstractModel	trainModel(int iterations, SequenceStream<Event> sequenceStream, int cutoff, boolean useAverage)	Trains a PerceptronModel with given parameters.
void	validate()	Checks the configured parameters.

Von Klasse geerbte Methoden opennlp.tools.ml.AbstractEventModelSequenceTrainer

train

Von Klasse geerbte Methoden opennlp.tools.ml.AbstractTrainer

getAlgorithm, getCutoff, getIterations, init

Von Klasse geerbte Methoden java.lang.Object

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

Von Schnittstelle geerbte Methoden opennlp.tools.commons.Trainer

init

Felddetails

PERCEPTRON_SEQUENCE_VALUE

public static final String PERCEPTRON_SEQUENCE_VALUE

Siehe auch:

• Konstantenfeldwerte

Konstruktordetails

SimplePerceptronSequenceTrainer

public SimplePerceptronSequenceTrainer()

Instantiates a SimplePerceptronSequenceTrainer with a default configuration of training parameters.

Methodendetails

validate

public void validate()

Checks the configured parameters. If a subclass overrides this, it should call super.validate();.

Setzt außer Kraft:

validate in Klasse AbstractTrainer

Löst aus:

IllegalArgumentException - Thrown if the algorithm name is not equal to {PERCEPTRON_SEQUENCE_VALUE}.

doTrain

public AbstractModel doTrain(SequenceStream<Event> events)
                      throws IOException

Angegeben von:

doTrain in Klasse AbstractEventModelSequenceTrainer

Löst aus:

IOException

trainModel

public AbstractModel trainModel(int iterations,
 SequenceStream<Event> sequenceStream,
 int cutoff,
 boolean useAverage)
                         throws IOException

Trains a PerceptronModel with given parameters.

Parameter:

iterations - The number of iterations to use for training.

sequenceStream - The SequenceStream<Event> used as data input.

cutoff - The {TrainingParameters.CUTOFF_PARAM} value to use for training.

useAverage - Whether to use 'averaging', or not.

Gibt zurück:

A valid, trained perceptron model.

Löst aus:

IOException

nextIteration

public void nextIteration(int iteration)
                   throws IOException

Löst aus:

IOException