Gerald Salton

Learn More
Automatic information retrieval systems must be designed to serve a multiplicity of users, each of whom may have different needs and may consequently require different kinds of service. Under these circumstances, it appears reasonable that the system should reflect this diversity of requirements by providing a role for the user in determining the search(More)
A great deal of effort has been devoted in recent years to the evaluation of automatic or semi-automatic information retrieval systems. Recent evaluation results indicate that the search effectiveness presently achieved, or likely to be achievable in the foreseeable future, is much smaller than expected by a majority of the potential user population.(More)
Abstract: Automatic text analysis methods are available that can assign identifying elements, or terms, to written documents, based on statistical and other formal criteria. Attempts to refine the established single-term indexing methods by using more complex syntactic and/or semantic methods have been unsuccessful. The problems relating to the(More)
The comparison between stored information identifications and requests for information is one of the principal tasks to be performed in automatic information retrieval. In so-called descriptor systems, where information is represented by sets of independent key words, this operation is relatively simple, since it consists of a comparison between the(More)
An automatic document retrieval system, programmed for the IBM 7094, is described. The system is designed to process English texts and search requests, and uses statistical, syntactic and semantic procedures for the analysis of information and the identification of relevant items. The operations are planned around a central supervisor, which in turn calls(More)
This paper describes document models and relations for the retrieval document images. The underlying methodology was developed for the Intelligent Document Image Retrieval System (IDIR) aims to extend document image database query capabilities. Traditional component type and keyword features are insufficient in describing logical and structural aspects of(More)
The lack of proper indexing and ranking techniques for Telugu documents motivated us for implementation of this work. The results provide a way to analyze efficiency of algorithms used for indexing and ranking. This paper summarizes the Automatic Term Weighting and Inverted File Structure approaches for Telugu documents and provides baseline of single term(More)
  • 1