Discusses intelligent filtering systems and describes work in the INFOS (Intelligent News Filtering Organizational System) project designed to automatically categorize data as relevant or irrelevant based on user interests. The filtering is performed by combining keyword-based hill climbing, knowledge-based conceptual representation via WordNet,…

Discusses the use of natural language captions versus content analysis for retrieving multimedia data such as pictures. Topics addressed include using caption syntax; additional inferences from captions; supercaptions; integrating content analysis; and results of experiments on an expert system with pictures. (Contains 11 references.) (LRW)

Describes the National Agricultural Library's microcomputer-based expert system, which is designed to help users obtain answers to simple reference questions. Building of the system and its linking to external programs and systems are explained, and building of a total information system is proposed. Samples of the program are provided. (CDD)

This report focuses on the user of a prototype hypertext application designed to help coin collectors link ancient coins with relevant numismatic information. It is noted that hypertext systems promote the collection of information that may be multimedia in nature and may be linked so that information can be accessed in a non-linear manner. The…

Information retrieval on the World Wide Web has a major obstacle: although data is abundant, it is unlabeled and randomly indexed. This paper discusses the implementation of a consultative Web search engine that minimizes the expertise level that is required from a user to accomplish an advanced search session. The system takes advantage of the…