public class LMJelinekMercerSimilarity extends LMSimilarity
The model has a single parameter, λ. According to said paper, the
optimal value depends on both the collection and the query. The optimal value
is around 0.1
for title queries and 0.7
for long queries.
LMSimilarity.CollectionModel, LMSimilarity.DefaultCollectionModel, LMSimilarity.LMStats
Similarity.SimScorer, Similarity.SimWeight
Constructor and Description |
---|
LMJelinekMercerSimilarity(float lambda)
Instantiates with the specified λ parameter.
|
LMJelinekMercerSimilarity(LMSimilarity.CollectionModel collectionModel,
float lambda)
Instantiates with the specified collectionModel and λ parameter.
|
Modifier and Type | Method and Description |
---|---|
float |
getLambda()
Returns the λ parameter.
|
String |
getName()
Returns the name of the LM method.
|
toString
computeNorm, computeWeight, getDiscountOverlaps, log2, setDiscountOverlaps, simScorer
coord, queryNorm
public LMJelinekMercerSimilarity(LMSimilarity.CollectionModel collectionModel, float lambda)
public LMJelinekMercerSimilarity(float lambda)
public float getLambda()
public String getName()
LMSimilarity
Used in LMSimilarity.toString()
getName
in class LMSimilarity
Copyright © 2010 - 2020 Adobe. All Rights Reserved