edu.ucla.sspace.wordsi

Class WordOccrrenceContextGenerator

java.lang.Object

edu.ucla.sspace.wordsi.WordOccrrenceContextGenerator

All Implemented Interfaces:

ContextGenerator

public class WordOccrrenceContextGenerator
extends Object
implements ContextGenerator

A raw word co-occurrence ContextGenerator. Each co-occurring word is mapped to a unique dimension and feature scores are based on the distance between the co-occurring word and the focus word in a particular context.

Author:

Keith Stevens

Constructor Summary

Constructors

Constructor and Description
WordOccrrenceContextGenerator(BasisMapping<String,String> basis, WeightingFunction weighting, int windowSize) Creates a new WordOccrrenceContextGenerator.

Method Summary

Methods

Modifier and Type	Method and Description
protected void	addContextTerms(SparseDoubleVector meaning, Queue<String> words, int distance) Adds a feature for each word in the context that has a valid dimension.
SparseDoubleVector	generateContext(Queue<String> prevWords, Queue<String> nextWords) 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

WordOccrrenceContextGenerator

public WordOccrrenceContextGenerator(BasisMapping<String,String> basis,
                             WeightingFunction weighting,
                             int windowSize)

Creates a new WordOccrrenceContextGenerator.

Parameters:

weighting - The WeightingFunction used to score each word co-occrrence, based on the distance from the focus word

windowSize - The size of the sliding symmetric window composing a context

Method Detail

generateContext

public SparseDoubleVector generateContext(Queue<String> prevWords,
                                 Queue<String> nextWords)

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 ContextGenerator

getVectorLength

public int getVectorLength()

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

Specified by:

getVectorLength in interface ContextGenerator

setReadOnly

public void setReadOnly(boolean readOnly)

Sets the read only mode of the ContextGenerator. While in read only mode, only features that previously existed will contribute to context vectors.

Specified by:

setReadOnly in interface ContextGenerator

addContextTerms

protected void addContextTerms(SparseDoubleVector meaning,
                   Queue<String> words,
                   int distance)

Adds a feature for each word in the context that has a valid dimension. Feature are scored based on the context word's distance from the focus word.