Package org.apache.lucene.search.similarities

Class AxiomaticF3EXP

java.lang.Object
org.apache.lucene.search.similarities.Similarity
org.apache.lucene.search.similarities.SimilarityBase
org.apache.lucene.search.similarities.Axiomatic
org.apache.lucene.search.similarities.AxiomaticF3EXP
public class AxiomaticF3EXP extends Axiomatic
F3EXP is defined as Sum(tf(term_doc_freq)*IDF(term)-gamma(docLen, queryLen)) where IDF(t) = pow((N+1)/df(t), k) N=total num of docs, df=doc freq gamma(docLen, queryLen) = (docLen-queryLen)*queryLen*s/avdl NOTE: the gamma function of this similarity creates negative scores
WARNING: This API is experimental and might change in incompatible ways in the next release.

  • Constructor Details

    • AxiomaticF3EXP

      public AxiomaticF3EXP(float s, int queryLen, float k)
      Constructor setting all Axiomatic hyperparameters
      Parameters:
      s - hyperparam for the growth function
      queryLen - the query length
      k - hyperparam for the primitive weighting function

    • AxiomaticF3EXP

      public AxiomaticF3EXP(float s, int queryLen)
      Constructor setting s and queryLen, letting k to default
      Parameters:
      s - hyperparam for the growth function
      queryLen - the query length

  • Method Details

    • toString

      public String toString()
      Description copied from class: Axiomatic
      Name of the axiomatic method.
      Specified by:
      toString in class Axiomatic

    • tf

      protected double tf(BasicStats stats, double freq, double docLen)
      compute the term frequency component
      Specified by:
      tf in class Axiomatic

    • ln

      protected double ln(BasicStats stats, double freq, double docLen)
      compute the document length component
      Specified by:
      ln in class Axiomatic

    • tfln

      protected double tfln(BasicStats stats, double freq, double docLen)
      compute the mixed term frequency and document length component
      Specified by:
      tfln in class Axiomatic

    • idf

      protected double idf(BasicStats stats, double freq, double docLen)
      compute the inverted document frequency component
      Specified by:
      idf in class Axiomatic

    • gamma

      protected double gamma(BasicStats stats, double freq, double docLen)
      compute the gamma component
      Specified by:
      gamma in class Axiomatic

    • tfExplain

      protected Explanation tfExplain(BasicStats stats, double freq, double docLen)
      Description copied from class: Axiomatic
      Explain the score of the term frequency component for a single document
      Specified by:
      tfExplain in class Axiomatic
      Parameters:
      stats - the corpus level statistics
      freq - number of occurrences of term in the document
      docLen - the document length
      Returns:
      Explanation of how the tf component was computed

    • lnExplain

      protected Explanation lnExplain(BasicStats stats, double freq, double docLen)
      Description copied from class: Axiomatic
      Explain the score of the document length component for a single document
      Specified by:
      lnExplain in class Axiomatic
      Parameters:
      stats - the corpus level statistics
      freq - number of occurrences of term in the document
      docLen - the document length
      Returns:
      Explanation of how the ln component was computed

    • tflnExplain

      protected Explanation tflnExplain(BasicStats stats, double freq, double docLen)
      Description copied from class: Axiomatic
      Explain the score of the mixed term frequency and document length component for a single document
      Specified by:
      tflnExplain in class Axiomatic
      Parameters:
      stats - the corpus level statistics
      freq - number of occurrences of term in the document
      docLen - the document length
      Returns:
      Explanation of how the tfln component was computed

    • idfExplain

      protected Explanation idfExplain(BasicStats stats, double freq, double docLen)
      Description copied from class: Axiomatic
      Explain the score of the inverted document frequency component for a single document
      Specified by:
      idfExplain in class Axiomatic
      Parameters:
      stats - the corpus level statistics
      freq - number of occurrences of term in the document
      docLen - the document length
      Returns:
      Explanation of how the idf component was computed