dragon.ir.kngbase

Class TopicSignatureModel

java.lang.Object

dragon.ir.kngbase.TopicSignatureModel

public class TopicSignatureModel
extends Object

A program for topic signature model estimation

This program finds a set of weighted terms to represent the semantics of a topic signature. A topic signature can be anything here including multiword phrases, concept pairs, and individual terms. There are two approaches to thee model estimation. One is the maximum likelihood estimator. The other uses EM algoritm if one can provide the disbribution of individual terms on a corpus. See more details about the EM algorithm in our previous work.

Zhou, X., Zhang, X., and Hu, X., Semantic Smoothing of Document Models for Agglomerative Clustering, In the Twentieth International Joint Conference on Artificial Intelligence(IJCAI 07), Hyderabad, India, Jan 6-12, 2007, pp. 2928-2933

One should provide indices for topic signatures and individual terms, respectively, or give the occurrence matrix of topic signatures and individual terms.

Copyright: Copyright (c) 2005

Company: IST, Drexel University

Version:

1.0

Author:

Davis Zhou

Constructor Summary

Constructors

Constructor and Description
TopicSignatureModel(IRSignatureIndexList srcIndexList, IntSparseMatrix cooccurMatrix) The constructor for the mode of the maximum likelihood estimator
TopicSignatureModel(IRSignatureIndexList srcIndexList, IntSparseMatrix srcSignatureDocMatrix, IntSparseMatrix destDocSignatureMatrix) The constructor for the mode of the maximum likelihood estimator
TopicSignatureModel(IRSignatureIndexList srcIndexList, IntSparseMatrix srcSignatureDocMatrix, IRSignatureIndexList destIndexList, IntSparseMatrix destDocSignatureMatrix) The constructor for the mode of EM algorithm
TopicSignatureModel(IRSignatureIndexList srcIndexList, IRSignatureIndexList destIndexList, IntSparseMatrix cooccurMatrix) The constructor for the mode of EM algorithm

Method Summary

Modifier and Type	Method and Description
ArrayList	genSignatureTranslation(int srcSignatureIndex)
boolean	genTransMatrix(int minDocFrequency, String matrixPath, String matrixKey)
double	getEMBackgroundCoefficient()
int	getEMIterationNum()
double	getProbThreshold()
boolean	getUseDocFrequency()
boolean	getUseEM()
boolean	getUseMeanTrim()
void	setEMBackgroundCoefficient(double coeffi)
void	setEMIterationNum(int iterationNum)
void	setProbThreshold(double threshold)
void	setUseDocFrequency(boolean option)
void	setUseEM(boolean option)
void	setUseMeanTrim(boolean option)

Methods inherited from class java.lang.Object

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

Constructor Detail

TopicSignatureModel

public TopicSignatureModel(IRSignatureIndexList srcIndexList,
                           IntSparseMatrix srcSignatureDocMatrix,
                           IntSparseMatrix destDocSignatureMatrix)

The constructor for the mode of the maximum likelihood estimator

Parameters:

srcIndexList - the statisitcs of topic signatures in the collection.

srcSignatureDocMatrix - the doc-term matrix for topic signatures.

destDocSignatureMatrix - the doc-term matrix for individual terms topic signatures will translate to.

TopicSignatureModel

public TopicSignatureModel(IRSignatureIndexList srcIndexList,
                           IntSparseMatrix cooccurMatrix)

The constructor for the mode of the maximum likelihood estimator

Parameters:

srcIndexList - the statisitcs of topic signatures in the collection.

cooccurMatrix - the cooccurence matrix of topic signatures and individual terms.

TopicSignatureModel

public TopicSignatureModel(IRSignatureIndexList srcIndexList,
                           IRSignatureIndexList destIndexList,
                           IntSparseMatrix cooccurMatrix)

The constructor for the mode of EM algorithm

Parameters:

srcIndexList - the statisitcs of topic signatures in the collection.

destIndexList - the statisitcs of individual terms in the collection.

cooccurMatrix - the cooccurence matrix of topic signatures and individual terms.

TopicSignatureModel

public TopicSignatureModel(IRSignatureIndexList srcIndexList,
                           IntSparseMatrix srcSignatureDocMatrix,
                           IRSignatureIndexList destIndexList,
                           IntSparseMatrix destDocSignatureMatrix)

The constructor for the mode of EM algorithm

Parameters:

srcIndexList - the statisitcs of topic signatures in the collection.

srcSignatureDocMatrix - srcSignatureDocMatrix the doc-term matrix for topic signatures.

destIndexList - the statisitcs of individual terms in the collection.

destDocSignatureMatrix - destDocSignatureMatrix the doc-term matrix for individual terms topic signatures will translate to.

Method Detail

setUseEM

public void setUseEM(boolean option)

getUseEM

public boolean getUseEM()

setEMBackgroundCoefficient

public void setEMBackgroundCoefficient(double coeffi)

getEMBackgroundCoefficient

public double getEMBackgroundCoefficient()

setEMIterationNum

public void setEMIterationNum(int iterationNum)

getEMIterationNum

public int getEMIterationNum()

setUseDocFrequency

public void setUseDocFrequency(boolean option)

getUseDocFrequency

public boolean getUseDocFrequency()

setUseMeanTrim

public void setUseMeanTrim(boolean option)

getUseMeanTrim

public boolean getUseMeanTrim()

setProbThreshold

public void setProbThreshold(double threshold)

getProbThreshold

public double getProbThreshold()

genTransMatrix

public boolean genTransMatrix(int minDocFrequency,
                              String matrixPath,
                              String matrixKey)

genSignatureTranslation

public ArrayList genSignatureTranslation(int srcSignatureIndex)