Class BasicModelD
java.lang.Object
org.apache.lucene.search.similarities.BasicModel
org.apache.lucene.search.similarities.BasicModelD
Implements the approximation of the binomial model with the divergence
for DFR. The formula used in Lucene differs slightly from the one in the
original paper: to avoid underflow for small values of
N
and
F
, N
is increased by 1
and
F
is always increased by tfn+1
.
WARNING: for terms that do not meet the expected random distribution (e.g. stopwords), this model may give poor performance, such as abnormally high scores for low tf values.
-
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptionfinal float
score
(BasicStats stats, float tfn) Returns the informative content score.toString()
Subclasses must override this method to return the code of the basic model formula.Methods inherited from class org.apache.lucene.search.similarities.BasicModel
explain
-
Constructor Details
-
BasicModelD
public BasicModelD()Sole constructor: parameter-free
-
-
Method Details
-
score
Description copied from class:BasicModel
Returns the informative content score.- Specified by:
score
in classBasicModel
-
toString
Description copied from class:BasicModel
Subclasses must override this method to return the code of the basic model formula. Refer to the original paper for the list.- Specified by:
toString
in classBasicModel
-