This report summarizes the work carried out on the automatic construction of keyword classifications and their use in information retrieval. It discusses the possible characteristics of such classifications, and potential ways of using them; and describes the various approaches to classification that were considered in terms of an overall frame of…

Investigates the feasibility of using a distance measure for automatic sequential document classification. This property of the distance measure is used to design a sequential classification algorithm which classifies key words and analyzes them separately in order to assign primary and secondary classes to a document. (VT)

Presents adaptation of a probabilistic theoretical model previously used in relevance feedback for use in automatic indexing of documents (in the sense of imitating) human indexers. Methods for model application are proposed, independence assumptions used in the model are interpreted, and the probability of a dependence model is discussed.…

The substitution information contained in automatically obtained keyword classification is most effectively exploited when: (1) strong similarity connectives only are utilized, (2) grouping is confined to non-frequent terms, (3) term groups are used to provide additional and not alternative descriptive items and (4) descriptor collection frequency…

Substantial alterations to a system often have little or no effect on particular collections. This may be due to poor separation of relevant and non-relevant documents. The paper presents a procedure for characterizing this separation, which can show whether proposed modifications of the base system are likely to be useful. (8 references)…

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)…

Part One, Automatic Content Analysis contains: "Content Analysis in Information Retrieval;""The 'Generality' Effect and the Retrieval Evaluation for Large Collections;""Automatic Indexing Using Bibliographic Citations" and "Automatic Resolution of Ambiguities from Natural Language Text." Part Two, Automatic…

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)

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)

This paper describes the process of automatic extraction of implicit--global--data from explicit information by file inversion and threading. Each datum is the symbolic representation of a proposition, and as such has a number of movable parts corresponding to the ideal elements of the proposition represented; e.g., subject, predicate. A third…

Demonstrates that the process of comparing each document in an automated system with all others during the classification procedure may be avoided by the use of an inverted file. (FM)

The report is concerned with the implementation of an on-line information storage and retrieval system for the Rome Air Development Center. This system is to incorporate techniques of automatic document classification for a large document collection in an interactive environment. Following a review of the system design, the implementation of the…

The paper reports on a series of programs that have been developed at the Moore School to process data-bases, consisting of textual items, and to index and arrange the data items in accordance with an automatically generated classification system. The programs produce the directories and the rearranged data-base on microfilm, where it may be…