org.terrier.matching.models.basicmodel

Class BM

java.lang.Object

org.terrier.matching.models.basicmodel.BasicModel

org.terrier.matching.models.basicmodel.BM

All Implemented Interfaces:

Serializable, Cloneable

public class BM
extends BasicModel

This class implements the BM weighting model, which generates the original weight given by the BM25 formula, without frequency normalisation and query term weighting. Feel free to combine the BM model with any frequency normalisation method. However, it is NOT recommended to use BM with the first normalisation for after effect. For example, to use the BM model with the normalisation 2, add the following line in file etc/trec.models: DFRWeightingModel(BM, , 2) Leave the space between the comas blank so that the first normalisation is disabled.

Author:

Ben He

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
protected String	modelName The name of the model.

Fields inherited from class org.terrier.matching.models.basicmodel.BasicModel

i, numberOfDocuments, numberOfTokens

Constructor Summary

Constructors

Constructor and Description
BM() A default constructor.

Method Summary

Methods

Modifier and Type	Method and Description
String	getInfo() Returns the name of the model.
double	score(double tf, double documentFrequency, double termFrequency, double keyFrequency, double documentLength) This method computes the score for the implemented weighting model.

Methods inherited from class org.terrier.matching.models.basicmodel.BasicModel

clone, setNumberOfDocuments, setNumberOfTokens, stirlingPower

Methods inherited from class java.lang.Object

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

Field Detail

modelName

protected String modelName

The name of the model.

Constructor Detail

BM

public BM()

A default constructor.

Method Detail

getInfo

public String getInfo()

Returns the name of the model.

Specified by:

getInfo in class BasicModel

Returns:

the name of the model

score

public double score(double tf,
           double documentFrequency,
           double termFrequency,
           double keyFrequency,
           double documentLength)

This method computes the score for the implemented weighting model.

Specified by:

score in class BasicModel

Parameters:

tf - The term frequency in the document

documentFrequency - The document frequency of the term

termFrequency - the term frequency in the collection

keyFrequency - The normalised query term frequency.

documentLength - The length of the document.

Returns:

the score returned by the implemented weighting model.