The logic of different types of weighting are discussed, and experiments testing weighting schemes of these types are described. The results show that one type of weighting leads to material performance improvements in quite different collection environments. (22 references) (Author)

Reports on a series of programs that have been developed to process data bases, consisting of textual items, and to index and arrange (classify) the data items in accordance with an automatically generated classification system. (Author)

An experiment in superficial indexing was carried out to elaborate the contract between indexing with a controlled vocabulary and using automated methods as described by Salton. (Author)

The use of a structured system of storing information, particularly relational indexing, can lead to situations in which items would not be retrieved due to technicalities of the system. To overcome such problems a study was made of condensations with the aim of providing a series of rules to apply. (4 references) (Author/SJ)

Heuristic methods for the construction of term classes are presented and experimental results are obtained to illustrate the usefulness of the method. (Author/PF)

An automatic classification technique using patterns formed by citations in document bibliographies was found to give 62 percent precision and 45 percent recall in a sample file of physics documents. (PF)

Describes a method for automatically segmenting words into their stems and affixes using certain statistical properties of a corpus to indicate where words should be divided. (Author/PF)

An experiment to compute and analyze the degree of association between descriptors used to index a document collection of approximately 40,000 records is described. An analysis of the results is presented which indicates the difficulties inherent in applying the results to an operating system. (11 references) (Author)

Three experiments were made by a flexible machine search system to test the retrieval efficiency of searching free text and keywords. Results based upon relevance judgements of users indicate that titles and abstracts are good index material which can be used for machine searching without human indexing. (Author/SJ)

Described is International Nickel's Technical Information System which involves cooperation between the London and New York offices. The problems of coordination, selection, vocabulary control, computer compatibility, communication and security are discussed. (4 references) (SJ)

Retrieval performance with automatic term classifications for three test collections has been variable. This paper attempts to discover why. The real difference between the collections is in the separation of relevant from non-relevant documents. The separation is so poor that classification cannot be expected to succeed. (14 references)…

Use of syntactic trace as an access strategy for large files containing arbitrary languages for which thesaurus-based and multiple attribute search techniques are unsuitable. (LS)

An evaluation of graph theoretical clusters of index terms which can be extracted from an automatically indexed document collection, and the effects of employing such clusters in automatic document retrieval are described. (19 references) (Author)