Reports on an evaluation of the construction of selective dissemination of information profiles for the International Nuclear Information System (INIS) in South Africa. (PF)

A procedure for adjusting queries to retrieve more documents for a user by automatically selecting and broadening the descriptors from relevant documents is described. Although more computing is required, recall and precision are superior to traditional searching. (KP)

The single-link cluster method is used to construct a hierarchic classification for the 1400 documents in the Cranfield test collection. A variety of retrieval strategies applied to this hierarchy are evaluated in terms of effectiveness and efficiency. (Author)

Reports of two experimental studies of uses of citing statements to augment full-text information retrieval of biomedical papers indicate that 78 percent of the words in computer-recognized citing statements were correctly attributable to corresponding cited papers, and computer procedures missed four percent of the words in the actual statements.…

Analyzes recent developments in the problem of processing queries expressed as Boolean expressions, shows that the concept of threshold values resolves the problems inherent with relevance weights, and explores possible evaluation mechanisms for document retrieval based on fuzzy set theory. Sixteen references are listed. (FM)

Discussion of retrieval overlap and relevant overlap focuses on an analysis of data from an earlier study on overlap among document representations. This new analysis investigated the odds that an item was judged relevant when it was retrieved by two search fields as opposed to being retrieved by only one field. (Contains 17 references.) (LRW)

Presents a general mathematical framework for information retrieval, in which query evaluation is seen as a mapping from the free term algebra built by query descriptors and weights to the semantic algebra of evaluation value. Competing mathematical models that try to describe how retrieval systems behave are reviewed. (Author/MBR)

An information retrieval system which aspires to retrieval of relevant documents should have second stage which will order topical set to provide maximum informativeness to requestor. A two-stage system concerned only with topicality can be iterated to generate a high recall set and discard imprecise documents without user input. (EJS)

Presents a model that places Boolean database queries into conjunctive normal form, thereby allowing probabilistic ranking of documents and the incorporation of relevance feedback. Experimental results compare the performance of a sequential learning probabilistic retrieval model with the proposed integrated Boolean probabilistic model and a fuzzy…

A report of several comparisons designed to measure the retrieval effectiveness of machined-aided indexing and manual indexing. (Author)

Describes GRANT, an expert system for finding sources of funding given research proposals. The architecture of GRANT and the implementation of constrained spreading activation (a modified search algorithm based on semantic memory) are described, and recall and precision rates are analyzed. (Author/LRW)

Describes large scale experiments to test the value of index term weighting based on relevance information, and presents results showing that weighting leads to remarkable improvements in retrieval performance. (Author/CWM)

Describes a model of an information retrieval system based on a thesaurus with weights. Appropriate terms are defined, and inclusiveness and two other fundamental properties of the system are presented. (CWM)

Discussion of search strategies in information retrieval systems focuses on the implementation of document ranking based on inverted files. Highlights include descriptions of three heuristic methods for implementing a weighting strategy and a comparison of two methods for estimating retrieval accuracy, including document movement and linear…

Describes a study that tested the effectiveness of a thesaurus as a search-aid in free text searching of a Finnish full text database. Linguistic and conceptual approaches are discussed; five search modes are explained; recall and precision are examined; and the use of proximity operators is discussed. (Contains 29 references.) (LRW)