ABSTRACT
Information retrieval (IR) systems aim to select relevant material from large collections of information in response to user queries. The approaches used to accomplish this have been the focus of much research and development, and have led to the algorithms underlying many commercial and Web-based search engines today.
This entry describes the common components that go into the design of IR systems (from text processing to inverted file indexes). The major classes (or models) of retrieval algorithms (Boolean, vector, and probabilistic) are described along with formal definitions of the basic form of these algorithms and some of the variations in common use in IR research. In addition, the entry examines query expansion techniques, and in particular relevance feedback, and how they are used in IR systems.
