edu.stanford.nlp.patterns.surface

Class LearnImportantFeatures

java.lang.Object

edu.stanford.nlp.patterns.surface.LearnImportantFeatures

public class LearnImportantFeatures
extends Object

The idea is that you can learn features that are important using ML algorithm and use those features in learning weights for patterns.

Author:

Sonal Gupta (sonalg@stanford.edu)

Field Summary

Fields

Modifier and Type	Field and Description
Class	answerClass
String	answerLabel

Constructor Summary

Constructors

Constructor and Description
LearnImportantFeatures()

Method Summary

Modifier and Type	Method and Description
static boolean	getRandomBoolean(Random random, double p)
Counter<String>	getTopFeatures(Iterator<Pair<Map<String,DataInstance>,File>> sentsf, double perSelectRand, double perSelectNeg, String externalFeatureWeightsFileLabel)
static void	main(String[] args)
void	setUp()

Methods inherited from class java.lang.Object

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

Field Detail

answerClass

@Execution.Option(name="answerClass")
public Class answerClass

answerLabel

@Execution.Option(name="answerLabel")
public String answerLabel

Constructor Detail

LearnImportantFeatures

public LearnImportantFeatures()

Method Detail

setUp

public void setUp()

getRandomBoolean

public static boolean getRandomBoolean(Random random,
                                       double p)

getTopFeatures

public Counter<String> getTopFeatures(Iterator<Pair<Map<String,DataInstance>,File>> sentsf,
                                      double perSelectRand,
                                      double perSelectNeg,
                                      String externalFeatureWeightsFileLabel)
                               throws IOException,
                                      ClassNotFoundException

Throws:

IOException

ClassNotFoundException

main

public static void main(String[] args)