Information retrieval (IR) aims at defining systems able to provide a fast and effective content-based access to a large amount of stored information. A promising direction to increase the effectiveness of IR is to model the concept of "partially intrinsic" in the IR process and to make the systems adaptive, i.e.

I. Fuzzy Set Theory.- A Framework for Linguistic and Hierarchical Queries in Document Retrieval.- Application of Fuzzy Set Theory to Extend Boolean Information Retrieval.- A Model of Intelligent Information Retrieval Using Fuzzy Tolerance Relations Based on Hierarchical Co-Occurrence of Words.- II. Neural Networks.- Visual Keywords: from Text Retrieval to Multimedia Retrieval.- Document Classification with Unsupervised Artificial Neural Networks.- The Java Search Agent Workshop.- A Connectionist Approach to Content Access in Documents: Application to Detection of Jokes.- III. Genetic Algorithms.- Connectionist and Genetic Approaches for Information Retrieval.- Large Population or Many Generations for Genetic Algorithms? Implications in Information Retrieval.- IV. Evidential and Probabilistic Reasoning.- A Logical Information Retrieval Model Based on a Combination of Propositional Logic and Probability Theory.- Bayesian Network Models for Information Retrieval.- Probabilistic Learning by Uncertainty Sampling with Non-Binary Relevance.- V. Rough Sets Theory, Multivalued Logics, and Other Approaches.- Granulär Information Retrieval.- A Framework for the Retrieval of Multimedia Objects Based on Four-Valued Fuzzy Description Logics.- Rough and Fuzzy Sets for Data Mining of a Controlled Vocabulary for Textual Retrieval.- Rough Sets and Multisets in a Model of Information Retrieval.