lemur::retrieval::XLingDocModel Class Reference

Doc representation for cross lingual retrieval model. More...

#include <XLingDocModel.hpp>

Inheritance diagram for lemur::retrieval::XLingDocModel:

List of all members.

Public Member Functions
	XLingDocModel (lemur::api::DOCID_T docID, const lemur::api::Index *ind, double l, double nt, bool sM=false)
	Constructor taking optional parameters for smoothing.
	~XLingDocModel ()
virtual double	termWeight (lemur::api::TERMID_T termID, const lemur::api::DocInfo *info) const
	Computes term weight for a given term.
virtual double	scoreConstant () const
Protected Attributes
const lemur::api::Index *	refIndex
	Index for the collection.
double	numTerms
	denominator (number of terms) for background model probability estimate.
double	lambda
	smoothing coefficient
bool	docBasedSmooth
	Use term frequency (tf/|V|) when false, use term doc frequency (docCount(t)/Sum_w_in_V(docCount(w))) when true for the background model.

---

Detailed Description

Doc representation for cross lingual retrieval model.

---

Constructor & Destructor Documentation

lemur::retrieval::XLingDocModel::XLingDocModel (  lemur::api::DOCID_T  docID, const lemur::api::Index *  ind, double  l, double  nt, bool  sM = false )  [inline]

Constructor taking optional parameters for smoothing. Parameters: docID  internal document id for this document. ind  pointer to Index for the document. l  lambda value to use for smoothing term weights. nt  |V| (sM false) or docCount(t)/Sum_w_in_V(docCount(w)) (sM true) sM  whether to use term frequency (tf/|V|) or term doc frequency (docCount(t)/Sum_w_in_V(docCount(w))) for the background model. Default is term frequency.

lemur::retrieval::XLingDocModel::~XLingDocModel (   )  [inline]

---

Member Function Documentation

virtual double lemur::retrieval::XLingDocModel::scoreConstant (   )  const [inline, virtual]

Unused. Returns: lambda Implements lemur::api::DocumentRep.

virtual double lemur::retrieval::XLingDocModel::termWeight (  lemur::api::TERMID_T  termID, const lemur::api::DocInfo *  info )  const [inline, virtual]

Computes term weight for a given term. Parameters: termID  the term info  the DocInfo for this document Returns: the smoothed term weight for the term using lambda*(dtf/|D|) + (1-lambda)*P(t|C) where P(t|C) is either term frequency (tf/|V|) or term doc frequency (docCount(t)/Sum_w_in_V(docCount(w))).

---

Member Data Documentation

bool lemur::retrieval::XLingDocModel::docBasedSmooth [protected]

Use term frequency (tf/|V|) when false, use term doc frequency (docCount(t)/Sum_w_in_V(docCount(w))) when true for the background model.

double lemur::retrieval::XLingDocModel::lambda [protected]

smoothing coefficient

double lemur::retrieval::XLingDocModel::numTerms [protected]

denominator (number of terms) for background model probability estimate.

const lemur::api::Index* lemur::retrieval::XLingDocModel::refIndex [protected]

Index for the collection.

---

The documentation for this class was generated from the following file:

• XLingDocModel.hpp

---