Ranked Neuro Fuzzy Inference System (RNFIS) for Information Retrieval

摘要

The paper presents a novel approach to informational retrieval based on a synergy of knowledge-based models, set theoretic models, and vector space models of domain within a Fuzzy Logic framework. An input query is expanded to multiple synonym queries based on query semantics. Each document in the collection is divided into different zones with different relative importance assigned to each zone indicating its role in the query. Fuzzy rule bases are applied to each zone with parameters derived from vector space models and semantic query expansion. Fuzzy inference procedure outputs the relevance rank of each zone in satisfying the query. The relevance ranks of different zones are aggregated using the Ordered Weighted Averaging (OWA) operator to get the overall relevance rank of the complete document. The documents are ranked according to their relevance. The system has been tested on a standard dataset and has been demonstrated to show improved performance over typical vector space based approaches.