org.apache.lucene.search.similarities
Class TFIDFSimilarity

java.lang.Object
  extended by org.apache.lucene.search.similarities.Similarity
      extended by org.apache.lucene.search.similarities.TFIDFSimilarity
Direct Known Subclasses:
DefaultSimilarity

public abstract class TFIDFSimilarity
extends Similarity

Implementation of Similarity with the Vector Space Model.

Expert: Scoring API.

TFIDFSimilarity defines the components of Lucene scoring. Overriding computation of these components is a convenient way to alter Lucene scoring.

Suggested reading: Introduction To Information Retrieval, Chapter 6.

The following describes how Lucene scoring evolves from underlying information retrieval models to (efficient) implementation. We first brief on VSM Score, then derive from it Lucene's Conceptual Scoring Formula, from which, finally, evolves Lucene's Practical Scoring Function (the latter is connected directly with Lucene classes and methods).

Lucene combines Boolean model (BM) of Information Retrieval with Vector Space Model (VSM) of Information Retrieval - documents "approved" by BM are scored by VSM.

In VSM, documents and queries are represented as weighted vectors in a multi-dimensional space, where each distinct index term is a dimension, and weights are Tf-idf values.

VSM does not require weights to be Tf-idf values, but Tf-idf values are believed to produce search results of high quality, and so Lucene is using Tf-idf. Tf and Idf are described in more detail below, but for now, for completion, let's just say that for given term t and document (or query) x, Tf(t,x) varies with the number of occurrences of term t in x (when one increases so does the other) and idf(t) similarly varies with the inverse of the number of index documents containing term t.

VSM score of document d for query q is the Cosine Similarity of the weighted query vectors V(q) and V(d):
 

cosine-similarity(q,d)   =  
V(q) · V(d)
–––––––––
|V(q)| |V(d)|
VSM Score

 
Where V(q) · V(d) is the dot product of the weighted vectors, and |V(q)| and |V(d)| are their Euclidean norms.

Note: the above equation can be viewed as the dot product of the normalized weighted vectors, in the sense that dividing V(q) by its euclidean norm is normalizing it to a unit vector.

Lucene refines VSM score for both search quality and usability:

Under the simplifying assumption of a single field in the index, we get Lucene's Conceptual scoring formula:
 

score(q,d)   =   coord-factor(q,d) ·   query-boost(q) ·  
V(q) · V(d)
–––––––––
|V(q)|
  ·   doc-len-norm(d)   ·   doc-boost(d)
Lucene Conceptual Scoring Formula

 

The conceptual formula is a simplification in the sense that (1) terms and documents are fielded and (2) boosts are usually per query term rather than per query.

We now describe how Lucene implements this conceptual scoring formula, and derive from it Lucene's Practical Scoring Function.

For efficient score computation some scoring components are computed and aggregated in advance:

Lucene's Practical Scoring Function is derived from the above. The color codes demonstrate how it relates to those of the conceptual formula:

score(q,d)   =   coord(q,d)  ·  queryNorm(q)  ·  ( tf(t in d)  ·  idf(t)2  ·  t.getBoost() ·  norm(t,d) )
t in q
Lucene Practical Scoring Function

where

  1. tf(t in d) correlates to the term's frequency, defined as the number of times term t appears in the currently scored document d. Documents that have more occurrences of a given term receive a higher score. Note that tf(t in q) is assumed to be 1 and therefore it does not appear in this equation, However if a query contains twice the same term, there will be two term-queries with that same term and hence the computation would still be correct (although not very efficient). The default computation for tf(t in d) in DefaultSimilarity is:
     
    tf(t in d)   =   frequency½

     
  2. idf(t) stands for Inverse Document Frequency. This value correlates to the inverse of docFreq (the number of documents in which the term t appears). This means rarer terms give higher contribution to the total score. idf(t) appears for t in both the query and the document, hence it is squared in the equation. The default computation for idf(t) in DefaultSimilarity is:
     
    idf(t)  =   1 + log (
    numDocs
    –––––––––
    docFreq+1
    )

     
  3. coord(q,d) is a score factor based on how many of the query terms are found in the specified document. Typically, a document that contains more of the query's terms will receive a higher score than another document with fewer query terms. This is a search time factor computed in coord(q,d) by the Similarity in effect at search time.
     
  4. queryNorm(q) is a normalizing factor used to make scores between queries comparable. This factor does not affect document ranking (since all ranked documents are multiplied by the same factor), but rather just attempts to make scores from different queries (or even different indexes) comparable. This is a search time factor computed by the Similarity in effect at search time. The default computation in DefaultSimilarity produces a Euclidean norm:
     
    queryNorm(q)   =   queryNorm(sumOfSquaredWeights)   =  
    1
    ––––––––––––––
    sumOfSquaredWeights½

     
    The sum of squared weights (of the query terms) is computed by the query Weight object. For example, a BooleanQuery computes this value as:
     
    sumOfSquaredWeights   =   q.getBoost() 2  ·  ( idf(t)  ·  t.getBoost() ) 2
    t in q

     
  5. t.getBoost() is a search time boost of term t in the query q as specified in the query text (see query syntax), or as set by application calls to setBoost(). Notice that there is really no direct API for accessing a boost of one term in a multi term query, but rather multi terms are represented in a query as multi TermQuery objects, and so the boost of a term in the query is accessible by calling the sub-query getBoost().
     
  6. norm(t,d) encapsulates a few (indexing time) boost and length factors: The computeNorm(org.apache.lucene.index.FieldInvertState) method is responsible for combining all of these factors into a single float.

    When a document is added to the index, all the above factors are multiplied. If the document has multiple fields with the same name, all their boosts are multiplied together:
     

    norm(t,d)   =   lengthNorm  ·  f.boost()
    field f in d named as t

     
    However the resulted norm value is encoded as a single byte before being stored. At search time, the norm byte value is read from the index directory and decoded back to a float norm value. This encoding/decoding, while reducing index size, comes with the price of precision loss - it is not guaranteed that decode(encode(x)) = x. For instance, decode(encode(0.89)) = 0.75.
     
    Compression of norm values to a single byte saves memory at search time, because once a field is referenced at search time, its norms - for all documents - are maintained in memory.
     
    The rationale supporting such lossy compression of norm values is that given the difficulty (and inaccuracy) of users to express their true information need by a query, only big differences matter.
     
    Last, note that search time is too late to modify this norm part of scoring, e.g. by using a different Similarity for search.
     

See Also:
IndexWriterConfig.setSimilarity(Similarity), IndexSearcher.setSimilarity(Similarity)

Nested Class Summary
 
Nested classes/interfaces inherited from class org.apache.lucene.search.similarities.Similarity
Similarity.ExactSimScorer, Similarity.SimWeight, Similarity.SloppySimScorer
 
Constructor Summary
TFIDFSimilarity()
          Sole constructor.
 
Method Summary
 long computeNorm(FieldInvertState state)
          Computes the normalization value for a field, given the accumulated state of term processing for this field (see FieldInvertState).
 Similarity.SimWeight computeWeight(float queryBoost, CollectionStatistics collectionStats, TermStatistics... termStats)
          Compute any collection-level weight (e.g.
abstract  float coord(int overlap, int maxOverlap)
          Computes a score factor based on the fraction of all query terms that a document contains.
 float decodeNormValue(byte b)
          Decodes a normalization factor stored in an index.
 byte encodeNormValue(float f)
          Encodes a normalization factor for storage in an index.
 Similarity.ExactSimScorer exactSimScorer(Similarity.SimWeight stats, AtomicReaderContext context)
          Creates a new Similarity.ExactSimScorer to score matching documents from a segment of the inverted index.
abstract  float idf(long docFreq, long numDocs)
          Computes a score factor based on a term's document frequency (the number of documents which contain the term).
 Explanation idfExplain(CollectionStatistics collectionStats, TermStatistics termStats)
          Computes a score factor for a simple term and returns an explanation for that score factor.
 Explanation idfExplain(CollectionStatistics collectionStats, TermStatistics[] termStats)
          Computes a score factor for a phrase.
abstract  float lengthNorm(FieldInvertState state)
          Compute an index-time normalization value for this field instance.
abstract  float queryNorm(float sumOfSquaredWeights)
          Computes the normalization value for a query given the sum of the squared weights of each of the query terms.
abstract  float scorePayload(int doc, int start, int end, BytesRef payload)
          Calculate a scoring factor based on the data in the payload.
abstract  float sloppyFreq(int distance)
          Computes the amount of a sloppy phrase match, based on an edit distance.
 Similarity.SloppySimScorer sloppySimScorer(Similarity.SimWeight stats, AtomicReaderContext context)
          Creates a new Similarity.SloppySimScorer to score matching documents from a segment of the inverted index.
abstract  float tf(float freq)
          Computes a score factor based on a term or phrase's frequency in a document.
 float tf(int freq)
          Computes a score factor based on a term or phrase's frequency in a document.
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Constructor Detail

TFIDFSimilarity

public TFIDFSimilarity()
Sole constructor. (For invocation by subclass constructors, typically implicit.)

Method Detail

coord

public abstract float coord(int overlap,
                            int maxOverlap)
Computes a score factor based on the fraction of all query terms that a document contains. This value is multiplied into scores.

The presence of a large portion of the query terms indicates a better match with the query, so implementations of this method usually return larger values when the ratio between these parameters is large and smaller values when the ratio between them is small.

Overrides:
coord in class Similarity
Parameters:
overlap - the number of query terms matched in the document
maxOverlap - the total number of terms in the query
Returns:
a score factor based on term overlap with the query

queryNorm

public abstract float queryNorm(float sumOfSquaredWeights)
Computes the normalization value for a query given the sum of the squared weights of each of the query terms. This value is multiplied into the weight of each query term. While the classic query normalization factor is computed as 1/sqrt(sumOfSquaredWeights), other implementations might completely ignore sumOfSquaredWeights (ie return 1).

This does not affect ranking, but the default implementation does make scores from different queries more comparable than they would be by eliminating the magnitude of the Query vector as a factor in the score.

Overrides:
queryNorm in class Similarity
Parameters:
sumOfSquaredWeights - the sum of the squares of query term weights
Returns:
a normalization factor for query weights

tf

public float tf(int freq)
Computes a score factor based on a term or phrase's frequency in a document. This value is multiplied by the idf(long, long) factor for each term in the query and these products are then summed to form the initial score for a document.

Terms and phrases repeated in a document indicate the topic of the document, so implementations of this method usually return larger values when freq is large, and smaller values when freq is small.

The default implementation calls tf(float).

Parameters:
freq - the frequency of a term within a document
Returns:
a score factor based on a term's within-document frequency

tf

public abstract float tf(float freq)
Computes a score factor based on a term or phrase's frequency in a document. This value is multiplied by the idf(long, long) factor for each term in the query and these products are then summed to form the initial score for a document.

Terms and phrases repeated in a document indicate the topic of the document, so implementations of this method usually return larger values when freq is large, and smaller values when freq is small.

Parameters:
freq - the frequency of a term within a document
Returns:
a score factor based on a term's within-document frequency

idfExplain

public Explanation idfExplain(CollectionStatistics collectionStats,
                              TermStatistics termStats)
Computes a score factor for a simple term and returns an explanation for that score factor.

The default implementation uses:

 idf(docFreq, searcher.maxDoc());
 
Note that CollectionStatistics.maxDoc() is used instead of IndexReader#numDocs() because also TermStatistics.docFreq() is used, and when the latter is inaccurate, so is CollectionStatistics.maxDoc(), and in the same direction. In addition, CollectionStatistics.maxDoc() is more efficient to compute

Parameters:
collectionStats - collection-level statistics
termStats - term-level statistics for the term
Returns:
an Explain object that includes both an idf score factor and an explanation for the term.

idfExplain

public Explanation idfExplain(CollectionStatistics collectionStats,
                              TermStatistics[] termStats)
Computes a score factor for a phrase.

The default implementation sums the idf factor for each term in the phrase.

Parameters:
collectionStats - collection-level statistics
termStats - term-level statistics for the terms in the phrase
Returns:
an Explain object that includes both an idf score factor for the phrase and an explanation for each term.

idf

public abstract float idf(long docFreq,
                          long numDocs)
Computes a score factor based on a term's document frequency (the number of documents which contain the term). This value is multiplied by the tf(int) factor for each term in the query and these products are then summed to form the initial score for a document.

Terms that occur in fewer documents are better indicators of topic, so implementations of this method usually return larger values for rare terms, and smaller values for common terms.

Parameters:
docFreq - the number of documents which contain the term
numDocs - the total number of documents in the collection
Returns:
a score factor based on the term's document frequency

lengthNorm

public abstract float lengthNorm(FieldInvertState state)
Compute an index-time normalization value for this field instance.

This value will be stored in a single byte lossy representation by encodeNormValue(float).

Parameters:
state - statistics of the current field (such as length, boost, etc)
Returns:
an index-time normalization value

computeNorm

public final long computeNorm(FieldInvertState state)
Description copied from class: Similarity
Computes the normalization value for a field, given the accumulated state of term processing for this field (see FieldInvertState).

Matches in longer fields are less precise, so implementations of this method usually set smaller values when state.getLength() is large, and larger values when state.getLength() is small.

Specified by:
computeNorm in class Similarity
Parameters:
state - current processing state for this field
Returns:
computed norm value

decodeNormValue

public float decodeNormValue(byte b)
Decodes a normalization factor stored in an index.

See Also:
encodeNormValue(float)

encodeNormValue

public byte encodeNormValue(float f)
Encodes a normalization factor for storage in an index.

The encoding uses a three-bit mantissa, a five-bit exponent, and the zero-exponent point at 15, thus representing values from around 7x10^9 to 2x10^-9 with about one significant decimal digit of accuracy. Zero is also represented. Negative numbers are rounded up to zero. Values too large to represent are rounded down to the largest representable value. Positive values too small to represent are rounded up to the smallest positive representable value.

See Also:
Field.setBoost(float), SmallFloat

sloppyFreq

public abstract float sloppyFreq(int distance)
Computes the amount of a sloppy phrase match, based on an edit distance. This value is summed for each sloppy phrase match in a document to form the frequency to be used in scoring instead of the exact term count.

A phrase match with a small edit distance to a document passage more closely matches the document, so implementations of this method usually return larger values when the edit distance is small and smaller values when it is large.

Parameters:
distance - the edit distance of this sloppy phrase match
Returns:
the frequency increment for this match
See Also:
PhraseQuery.setSlop(int)

scorePayload

public abstract float scorePayload(int doc,
                                   int start,
                                   int end,
                                   BytesRef payload)
Calculate a scoring factor based on the data in the payload. Implementations are responsible for interpreting what is in the payload. Lucene makes no assumptions about what is in the byte array.

Parameters:
doc - The docId currently being scored.
start - The start position of the payload
end - The end position of the payload
payload - The payload byte array to be scored
Returns:
An implementation dependent float to be used as a scoring factor

computeWeight

public final Similarity.SimWeight computeWeight(float queryBoost,
                                                CollectionStatistics collectionStats,
                                                TermStatistics... termStats)
Description copied from class: Similarity
Compute any collection-level weight (e.g. IDF, average document length, etc) needed for scoring a query.

Specified by:
computeWeight in class Similarity
Parameters:
queryBoost - the query-time boost.
collectionStats - collection-level statistics, such as the number of tokens in the collection.
termStats - term-level statistics, such as the document frequency of a term across the collection.
Returns:
SimWeight object with the information this Similarity needs to score a query.

exactSimScorer

public final Similarity.ExactSimScorer exactSimScorer(Similarity.SimWeight stats,
                                                      AtomicReaderContext context)
                                               throws IOException
Description copied from class: Similarity
Creates a new Similarity.ExactSimScorer to score matching documents from a segment of the inverted index.

Specified by:
exactSimScorer in class Similarity
Parameters:
stats - collection information from Similarity.computeWeight(float, CollectionStatistics, TermStatistics...)
context - segment of the inverted index to be scored.
Returns:
ExactSimScorer for scoring documents across context
Throws:
IOException - if there is a low-level I/O error

sloppySimScorer

public final Similarity.SloppySimScorer sloppySimScorer(Similarity.SimWeight stats,
                                                        AtomicReaderContext context)
                                                 throws IOException
Description copied from class: Similarity
Creates a new Similarity.SloppySimScorer to score matching documents from a segment of the inverted index.

Specified by:
sloppySimScorer in class Similarity
Parameters:
stats - collection information from Similarity.computeWeight(float, CollectionStatistics, TermStatistics...)
context - segment of the inverted index to be scored.
Returns:
SloppySimScorer for scoring documents across context
Throws:
IOException - if there is a low-level I/O error


Copyright © 2000-2013 Apache Software Foundation. All Rights Reserved.