PKDDialogue.TurnSemanticAnalyzer.GetTopNMatchingTurnsByDecompositionRelevanceToDocument Function
Instead of creating a basis by projecting words in the query, we create a basis by projecting words in each document. Then we project the query into that basis. So this is more of a backwards looking rhetorical relationship. We expect the question to be highly relevant to the answer, and not add any information in particular to the answer.

Public System.Collections.ArrayList GetTopNMatchingTurnsByDecompositionRelevanceToDocument (LSAModule.AbstractDocument, System.Collections.ArrayList, int)
  Type Name Description  
    LSAModule.AbstractDocument queryDocument    
    System.Collections.ArrayList orgTurns    
    int N    
  Return Description  
    System.Collections.ArrayList