Complexity Reduction in Lattice-Based Information Retrieval

Though lattice-based information representation has the advantage of providing efficient visual interface over textual display, the complexity of a lattice may grow rapidly with the size of the database. In this paper we formally draw the analogy between Vector Space Model and Concept Lattice, from which we introduce the notion of Term-Document Lattice as a model for information retrieval. We then propose to use the idea of quotient lattice to reduce the complexity of a Term-Document Lattice. The equivalence relation required to construct the quotient lattice is obtained by performing a Singular Value Decomposition on the original term-document matrix.