pitt.search.semanticvectors
Class VectorSearcher.VectorSearcherMaxSim

java.lang.Object
  pitt.search.semanticvectors.VectorSearcher
      pitt.search.semanticvectors.VectorSearcher.VectorSearcherMaxSim

Enclosing class:

VectorSearcher

public static class VectorSearcher.VectorSearcherMaxSim
extends VectorSearcher

Class for searching a vector store using minimum distance similarity.

Nested Class Summary

Nested classes/interfaces inherited from class pitt.search.semanticvectors.VectorSearcher

VectorSearcher.BalancedVectorSearcherPerm, VectorSearcher.VectorSearcherConvolutionSim, VectorSearcher.VectorSearcherCosine, VectorSearcher.VectorSearcherCosineSparse, VectorSearcher.VectorSearcherMaxSim, VectorSearcher.VectorSearcherPerm, VectorSearcher.VectorSearcherSubspaceSim, VectorSearcher.VectorSearcherTensorSim

Constructor Summary

VectorSearcher.VectorSearcherMaxSim(VectorStore queryVecStore, VectorStore searchVecStore, LuceneUtils luceneUtils, java.lang.String[] queryTerms)

Method Summary

float

getScore(float[] testVector) Scoring works by taking scalar product with disjunctSpace (which must by now be represented using an orthogonal basis).

Methods inherited from class pitt.search.semanticvectors.VectorSearcher

getNearestNeighbors

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

VectorSearcher.VectorSearcherMaxSim

public VectorSearcher.VectorSearcherMaxSim(VectorStore queryVecStore,
                                           VectorStore searchVecStore,
                                           LuceneUtils luceneUtils,
                                           java.lang.String[] queryTerms)
                                    throws ZeroVectorException

Parameters:

queryVecStore - Vector store to use for query generation.

searchVecStore - The vector store to search.

luceneUtils - LuceneUtils object to use for query weighting. (May be null.)

queryTerms - Terms that will be parsed and used to generate a query subspace.

Throws:

ZeroVectorException

Method Detail

getScore

public float getScore(float[] testVector)

Scoring works by taking scalar product with disjunctSpace (which must by now be represented using an orthogonal basis).

Specified by:

getScore in class VectorSearcher

Parameters:

testVector - Vector being tested.