edu.umd.hooka

Class PhrasePair

java.lang.Object

edu.umd.hooka.PhrasePair

All Implemented Interfaces:

Cloneable, Comparable, org.apache.hadoop.io.Writable, org.apache.hadoop.io.WritableComparable

public class PhrasePair
extends Object
implements org.apache.hadoop.io.WritableComparable, Cloneable

Author:

chris Notes: This class represents a pair of phrases, one from target language, one from source language, and an alignment

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	PhrasePair.SubPhraseCoordinates

Constructor Summary

Constructors

Constructor and Description
PhrasePair()
PhrasePair(Phrase f, Phrase e)
PhrasePair(Phrase f, Phrase e, Alignment a)
PhrasePair(String f, Vocab vocF, String e, Vocab vocE, String a)

Method Summary

Methods

Modifier and Type	Method and Description
Object	clone()
int	compareTo(Object o)
boolean	equals(Object o)
ArrayList<PhrasePair>	extractConsistentPhrasePairs(int maxPhraseLength)
ArrayList<PhrasePair.SubPhraseCoordinates>	extractConsistentSubPhraseCoordinates(int maxPhraseLength)
PhrasePair	extractMinimalConsistentPhrasePairContainingESpan(int eStart, int eEnd)
PhrasePair	extractSubPhrasePair(int startF, int endF, int startE, int endE)
PhrasePair	extractSubPhrasePair(PhrasePair.SubPhraseCoordinates c)
Alignment	getAlignment()
AlignmentPosteriorGrid	getAlignmentPosteriorGrid()
Phrase	getE()
Phrase	getF()
PhrasePair.SubPhraseCoordinates	getMinimalConsistentSubPhraseCoordsContainingESpan(int e_start, int e_end) Returns the smallest consistent phrase pair that contains [e_start,e_end] This is not efficient- don't use it where speed counts!
PhrasePair	getTranspose()
boolean	hasAlignment()
boolean	hasAlignmentPosteriors()
int	hashCode()
void	mergeEnglishWords(int i, int j, int newE)
float	ratioFtoE()
void	readFields(DataInput in)
void	setAlignment(Alignment a)
void	setAlignmentPosteriorGrid(AlignmentPosteriorGrid g)
void	setE(Phrase e)
void	setF(Phrase f)
void	splitEnglishWords(int i, int newE1, int newE2)
void	splitForeignWords(int j, int newF1, int newF2)
String	toString()
String	toString(Vocab vocF, Vocab vocE)
void	write(DataOutput out)

Methods inherited from class java.lang.Object

finalize, getClass, notify, notifyAll, wait, wait, wait

Constructor Detail

PhrasePair

public PhrasePair()

PhrasePair

public PhrasePair(Phrase f,
          Phrase e)

PhrasePair

public PhrasePair(Phrase f,
          Phrase e,
          Alignment a)

PhrasePair

public PhrasePair(String f,
          Vocab vocF,
          String e,
          Vocab vocE,
          String a)

Method Detail

clone

public Object clone()

Overrides:

clone in class Object

compareTo

public int compareTo(Object o)

Specified by:

compareTo in interface Comparable

hashCode

public int hashCode()

Overrides:

hashCode in class Object

getTranspose

public PhrasePair getTranspose()

getAlignment

public Alignment getAlignment()

equals

public boolean equals(Object o)

Overrides:

equals in class Object

ratioFtoE

public float ratioFtoE()

toString

public String toString()

Overrides:

toString in class Object

mergeEnglishWords

public void mergeEnglishWords(int i,
                     int j,
                     int newE)

splitEnglishWords

public void splitEnglishWords(int i,
                     int newE1,
                     int newE2)

splitForeignWords

public void splitForeignWords(int j,
                     int newF1,
                     int newF2)

toString

public String toString(Vocab vocF,
              Vocab vocE)

getE

public Phrase getE()

getF

public Phrase getF()

setE

public void setE(Phrase e)

setF

public void setF(Phrase f)

hasAlignment

public boolean hasAlignment()

setAlignment

public void setAlignment(Alignment a)

readFields

public void readFields(DataInput in)
                throws IOException

Specified by:

readFields in interface org.apache.hadoop.io.Writable

Throws:

IOException

write

public void write(DataOutput out)
           throws IOException

Specified by:

write in interface org.apache.hadoop.io.Writable

Throws:

IOException

hasAlignmentPosteriors

public boolean hasAlignmentPosteriors()

getAlignmentPosteriorGrid

public AlignmentPosteriorGrid getAlignmentPosteriorGrid()

setAlignmentPosteriorGrid

public void setAlignmentPosteriorGrid(AlignmentPosteriorGrid g)

extractSubPhrasePair

public PhrasePair extractSubPhrasePair(PhrasePair.SubPhraseCoordinates c)

extractSubPhrasePair

public PhrasePair extractSubPhrasePair(int startF,
                              int endF,
                              int startE,
                              int endE)

getMinimalConsistentSubPhraseCoordsContainingESpan

public PhrasePair.SubPhraseCoordinates getMinimalConsistentSubPhraseCoordsContainingESpan(int e_start,
                                                                                 int e_end)

Returns the smallest consistent phrase pair that contains [e_start,e_end] This is not efficient- don't use it where speed counts!

extractMinimalConsistentPhrasePairContainingESpan

public PhrasePair extractMinimalConsistentPhrasePairContainingESpan(int eStart,
                                                           int eEnd)

extractConsistentSubPhraseCoordinates

public ArrayList<PhrasePair.SubPhraseCoordinates> extractConsistentSubPhraseCoordinates(int maxPhraseLength)

extractConsistentPhrasePairs

public ArrayList<PhrasePair> extractConsistentPhrasePairs(int maxPhraseLength)