This article surveys probabilistic approaches to modeling information retrieval. The basic concepts of probabilistic approaches to information retrieval are outlined and the principles and assumptions upon which the approaches are based are presented. The various models proposed in the development of IR are described, classified, and compared using a common formalism. New approaches that constitute the basis of future research are described

We report on our first experiences in dealing with the retrieval of spoken documents. While lacking the tools and the know-how for performing speech recognition on the spoken documents, we tried to use in the best possible way our knowledge of probabilistic indexing and retrieval of textual documents. The techniques we used and the results we obtained are encouraging, motivating our future involvement in other further experimentation in this new area of research. Supported by a "Marie Curie" Research Fellowship from the European Community. Contents 1 Introduction 3 2 Probabilistic Information Retrieval 3 2.1 The binary independence retrieval model . . . . . . . . . . . . . . 4 2.2 Term weighting schemas . . . . . . . . . . . . . . . . . . . . . . . 9 3 The SIRE Information Retrieval system 11 4 The Abbot speech recognition system 12 5 Spoken document retrieval at TREC-6 14 6 The SDR TREC-6 data set 15 7 Experimenting probabilistic retrieval of spoken documents 18 7.1 The PFT wei...