edu.stanford.nlp.ie

Class EntityCachingAbstractSequencePrior<IN extends CoreMap>

java.lang.Object

edu.stanford.nlp.ie.EntityCachingAbstractSequencePrior<IN>

All Implemented Interfaces:

ListeningSequenceModel, SequenceListener, SequenceModel

Direct Known Subclasses:

EmpiricalNERPrior

public abstract class EntityCachingAbstractSequencePrior<IN extends CoreMap>
extends java.lang.Object
implements ListeningSequenceModel

This class keeps track of all labeled entities and updates its list whenever the label at a point gets changed. This allows you to not have to regenerate the list every time, which can be quite inefficient.

Author:

Jenny Finkel

Field Summary

Fields

Modifier and Type	Field and Description
protected int	backgroundSymbol
protected Index<java.lang.String>	classIndex
protected java.util.List<IN>	doc
protected int	numClasses
protected int[]	possibleValues
protected int[]	sequence

Constructor Summary

Constructors

Constructor and Description
EntityCachingAbstractSequencePrior(java.lang.String backgroundSymbol, Index<java.lang.String> classIndex, java.util.List<IN> doc)

Method Summary

Modifier and Type	Method and Description
boolean	addingSingletonEntity(int[] sequence, int position)
boolean	appendingEntity(int[] sequence, int position)
edu.stanford.nlp.ie.Entity	extractEntity(int[] sequence, int position) extracts the entity starting at the given position and adds it to the entity list.
double[]	getConditionalDistribution(int[] sequence, int position)
int	getNumClasses() get the number of classes in the sequence model.
int[]	getPossibleValues(int position) Return the valid sequence labels (as integer indices) for a particular position in the sequence.
boolean	joiningTwoEntities(int[] sequence, int position)
int	leftWindow() How many label positions to the left influence the label assignment at a particular position.
int	length()
boolean	matches(edu.stanford.nlp.ie.Entity entity, int position)
boolean	noChange(int[] sequence, int position)
int[]	otherOccurrences(edu.stanford.nlp.ie.Entity entity) finds other locations in the sequence where the sequence of words in this entity occurs.
boolean	prependingEntity(int[] sequence, int position)
boolean	removingBeginningOfEntity(int[] sequence, int position)
boolean	removingEndOfEntity(int[] sequence, int position)
int	rightWindow() How many label positions to the right influence the label assignment at a particular position.
double	scoreOf(int[] sequence, int pos) Computes the score of the element at the given position in the sequence, conditioned on the values of the elements in all other positions of the provided sequence.
double[]	scoresOf(int[] sequence, int position) Computes the scores of labels for the element at the given position in the sequence, conditioned on the values of the labels at all other positions of the provided sequence.
void	setInitialSequence(int[] initialSequence) Informs this sequence listener that the value of the whole sequence is initialized to sequence.
boolean	splittingTwoEntities(int[] sequence, int position)
static int[]	toArray(java.util.List<java.lang.Integer> list)
java.lang.String	toString()
java.lang.String	toString(int pos)
void	updateSequenceElement(int[] sequence, int position, int oldVal) Informs this sequence listener that the value of the element at position pos has changed.

Methods inherited from class java.lang.Object

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

Methods inherited from interface edu.stanford.nlp.sequences.SequenceModel

scoreOf

Field Detail

sequence

protected int[] sequence

backgroundSymbol

protected final int backgroundSymbol

numClasses

protected final int numClasses

possibleValues

protected final int[] possibleValues

classIndex

protected final Index<java.lang.String> classIndex

doc

protected final java.util.List<IN extends CoreMap> doc

Constructor Detail

EntityCachingAbstractSequencePrior

public EntityCachingAbstractSequencePrior(java.lang.String backgroundSymbol,
                                          Index<java.lang.String> classIndex,
                                          java.util.List<IN> doc)

Method Detail

leftWindow

public int leftWindow()

Description copied from interface: SequenceModel

How many label positions to the left influence the label assignment at a particular position.

Specified by:

leftWindow in interface SequenceModel

Returns:

The size of the left window used by this sequence model

rightWindow

public int rightWindow()

Description copied from interface: SequenceModel

How many label positions to the right influence the label assignment at a particular position.

Specified by:

rightWindow in interface SequenceModel

Returns:

the size of the right window used by this sequence model

getPossibleValues

public int[] getPossibleValues(int position)

Description copied from interface: SequenceModel

Return the valid sequence labels (as integer indices) for a particular position in the sequence. Since the sequence is padded at each end, typically sequence items 0...leftWindow-1 are null, leftWindow...length+leftWindow-1 are words, length+leftWindow...length+leftWindow+rightWindow-1 are null.

Specified by:

getPossibleValues in interface SequenceModel

Parameters:

position - The position

Returns:

The set of possible int values at this position, as an int array

scoreOf

public double scoreOf(int[] sequence,
                      int pos)

Description copied from interface: SequenceModel

Computes the score of the element at the given position in the sequence, conditioned on the values of the elements in all other positions of the provided sequence. Typically, this is an unnormalized log conditional probability of the label at the given position in the sequence, given the input data nd the other labels.

Specified by:

scoreOf in interface SequenceModel

Parameters:

sequence - The sequence containing the prediction and the rest of the labels to condition on

pos - The position of the element to give a score for

Returns:

The score of the label at the specified position in the sequence

length

public int length()

Specified by:

length in interface SequenceModel

Returns:

the length of the sequence

getNumClasses

public int getNumClasses()

get the number of classes in the sequence model.

getConditionalDistribution

public double[] getConditionalDistribution(int[] sequence,
                                           int position)

scoresOf

public double[] scoresOf(int[] sequence,
                         int position)

Description copied from interface: SequenceModel

Computes the scores of labels for the element at the given position in the sequence, conditioned on the values of the labels at all other positions of the provided sequence. The returned array elements correspond index-by-index to the possible values returned by getPossibleValues(int). The label at sequence[position] is ignored in the calculations. The scores are often given as an unnormalized log conditional distribution over possible labels. Otherwise, they may be probabilities. If it is a probability distribution, conceptually, the scores should sum to 1 (perhaps after transforming them). Note that implementations often alter sequence[position] to do their calculations, and so access to the array isn't threadsafe, but should restore its value afterwards.

Specified by:

scoresOf in interface SequenceModel

Parameters:

sequence - The sequence containing the rest of the values to condition on

position - The position of the element to give a distribution for

Returns:

The scores of the possible tokens at the specified position in the sequence

setInitialSequence

public void setInitialSequence(int[] initialSequence)

Description copied from interface: SequenceListener

Informs this sequence listener that the value of the whole sequence is initialized to sequence.

Specified by:

setInitialSequence in interface SequenceListener

extractEntity

public edu.stanford.nlp.ie.Entity extractEntity(int[] sequence,
                                                int position)

extracts the entity starting at the given position and adds it to the entity list. returns the index of the last element in the entity (not index+1)

otherOccurrences

public int[] otherOccurrences(edu.stanford.nlp.ie.Entity entity)

finds other locations in the sequence where the sequence of words in this entity occurs.

toArray

public static int[] toArray(java.util.List<java.lang.Integer> list)

matches

public boolean matches(edu.stanford.nlp.ie.Entity entity,
                       int position)

joiningTwoEntities

public boolean joiningTwoEntities(int[] sequence,
                                  int position)

splittingTwoEntities

public boolean splittingTwoEntities(int[] sequence,
                                    int position)

appendingEntity

public boolean appendingEntity(int[] sequence,
                               int position)

prependingEntity

public boolean prependingEntity(int[] sequence,
                                int position)

addingSingletonEntity

public boolean addingSingletonEntity(int[] sequence,
                                     int position)

removingEndOfEntity

public boolean removingEndOfEntity(int[] sequence,
                                   int position)

removingBeginningOfEntity

public boolean removingBeginningOfEntity(int[] sequence,
                                         int position)

noChange

public boolean noChange(int[] sequence,
                        int position)

updateSequenceElement

public void updateSequenceElement(int[] sequence,
                                  int position,
                                  int oldVal)

Description copied from interface: SequenceListener

Informs this sequence listener that the value of the element at position pos has changed. This allows this sequence model to update its internal model if desired.

Specified by:

updateSequenceElement in interface SequenceListener

toString

public java.lang.String toString()

Overrides:

toString in class java.lang.Object

toString

public java.lang.String toString(int pos)