FP-Tree motivated system for information retrieval using an abstraction path-based inverted index

Abstract

Language ontologies provide an avenue for automated lexical analysis that may be used in concert with existing information retrieval methods to allow lexicographic relationships to be considered in searches. This paper presents a method of information retrieval that uses WordNet, a database of lexical ontologies, to generate paths of abstraction via lexicographic relationships, and uses these relationships as the basis for an inverted index to be used in the retrieval of documents from an indexed corpus. We present this method as a entree to a line of research in using lexical ontologies to perform graph analysis of documents, and through this process improve the precision of existing information retrieval techniques.