kylm.model.ngram.smoother
Class NgramSmoother

java.lang.Object
  kylm.model.ngram.smoother.NgramSmoother

All Implemented Interfaces:

java.io.Serializable

Direct Known Subclasses:

AbsoluteSmoother, GTSmoother, MLSmoother, WBSmoother

public abstract class NgramSmoother
extends java.lang.Object
implements java.io.Serializable

An abstract class that defines an algorithm to smooth an n-gram model

Author:

neubig

See Also:

Serialized Form

Constructor Summary

NgramSmoother()

Method Summary

boolean	equals(java.lang.Object obj)
abstract java.lang.String	getAbbr()
int[]	getCutoffs()
int	getDebugLevel()
abstract java.lang.String	getName()
boolean	getSmoothUnigrams()
void	setCutoffs(int[] cutoffs)
void	setDebugLevel(int debug)
void	setSmoothUnigrams(boolean smoothUnigram)
abstract void	smooth(NgramLM lm) Smooth all the n-gram probabilities in a language model according to the appropriate smoothing algorithm.

Methods inherited from class java.lang.Object

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

Constructor Detail

NgramSmoother

public NgramSmoother()

Method Detail

smooth

public abstract void smooth(NgramLM lm)

Smooth all the n-gram probabilities in a language model according to the appropriate smoothing algorithm.

Parameters:

lm - The N-gram language model to smooth.

setSmoothUnigrams

public void setSmoothUnigrams(boolean smoothUnigram)

getSmoothUnigrams

public boolean getSmoothUnigrams()

equals

public boolean equals(java.lang.Object obj)

Overrides:

equals in class java.lang.Object

getDebugLevel

public int getDebugLevel()

setDebugLevel

public void setDebugLevel(int debug)

getCutoffs

public int[] getCutoffs()

setCutoffs

public void setCutoffs(int[] cutoffs)

getName

public abstract java.lang.String getName()

Returns:

The name of this type of smoothing

getAbbr

public abstract java.lang.String getAbbr()

Returns:

The abbreviation given to this type of smoothing