edu.ucla.sspace.wordsi

Class RandomIndexingDependencyContextGenerator

java.lang.Object

edu.ucla.sspace.wordsi.RandomIndexingDependencyContextGenerator

All Implemented Interfaces:

DependencyContextGenerator

public class RandomIndexingDependencyContextGenerator
extends Object
implements DependencyContextGenerator

A DependencyContextGenerator that forms context vectors using a summation of index vectors. Each index vector is fixed TernaryVector corresponding to each term in the corpus. Only index vectors for terms reachable by a valid DependencyPath starting from the focus wordwill be applied to a particular context.

Author:

Keith Stevens

Constructor Summary

Constructors

Constructor and Description
RandomIndexingDependencyContextGenerator(DependencyPermutationFunction<TernaryVector> permFunc, DependencyPathAcceptor acceptor, Map<String,TernaryVector> indexMap, int indexVectorLength, int pathLength) Creates a new RandomIndexingDependencyContextGenerator.

Method Summary

Methods

Modifier and Type	Method and Description
SparseDoubleVector	generateContext(DependencyTreeNode[] tree, int focusIndex) Returns a SparseDoubleVector that represents the context composed of the set of prevWords before the focus word and the set of nextWords after the focus word.
int	getVectorLength() Returns the maximum number of dimensions used to represent any given context.
void	setReadOnly(boolean readOnly) Sets the read only mode of the ContextGenerator.

Methods inherited from class java.lang.Object

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

Constructor Detail

RandomIndexingDependencyContextGenerator

public RandomIndexingDependencyContextGenerator(DependencyPermutationFunction<TernaryVector> permFunc,
                                        DependencyPathAcceptor acceptor,
                                        Map<String,TernaryVector> indexMap,
                                        int indexVectorLength,
                                        int pathLength)

Creates a new RandomIndexingDependencyContextGenerator.

Parameters:

permFunc - the DependencyPermutationFunction responsible for permuting TernaryVector, which serve as index vectors.

acceptor - The DependencyPathAcceptor used to validate DependencyPaths stemming from focus word.

indexMap - A mapping from word forms to TernaryVectors.

indexVectorLength - The length of each index vector.

pathLength - The maximum acceptable length of any DependencyPath.

Method Detail

generateContext

public SparseDoubleVector generateContext(DependencyTreeNode[] tree,
                                 int focusIndex)

Returns a SparseDoubleVector that represents the context composed of the set of prevWords before the focus word and the set of nextWords after the focus word. Since sparse vectors are returned, if a second order vector is generated, it is recommended that the vector also be sparsed or have very few dimensions.

Specified by:

generateContext in interface DependencyContextGenerator

getVectorLength

public int getVectorLength()

Returns the maximum number of dimensions used to represent any given context.

Specified by:

getVectorLength in interface DependencyContextGenerator

setReadOnly

public void setReadOnly(boolean readOnly)

Sets the read only mode of the ContextGenerator. When set to read only, it prevents any new features from being generated.

Specified by:

setReadOnly in interface DependencyContextGenerator