Applying multi-objective evolutionary algorithms to the automatic learning of extended Boolean queries in fuzzy ordinal linguistic information retrieval systems

摘要

The performance of information retrieval systems (IRSs) is usually measured using two different criteria, precision and recall. Precision is the ratio of the relevant documents retrieved by the IRS in response to a user's query to the total number of documents retrieved, whilst recall is the ratio of the number of relevant documents retrieved to the total number of relevant documents for the user's query that exist in the documentary database. In fuzzy ordinal linguistic IRSs (FOLIRSs), where extended Boolean queries are used, defining the user's queries in a manual way is usually a complex task. In this contribution, our interest is focused on the automatic learning of extended Boolean queries in FOLIRSs by means of multi-objective evolutionary algorithms considering both mentioned performance criteria. We present an analysis of two well-known general-purpose multi-objective evolutionary algorithms to learn extended Boolean queries in FOLIRSs. These evolutionary algorithms are the non-dominated sorting genetic algorithm (NSGA-II) and the strength Pareto evolutionary algorithm (SPEA2).