The work described was designed to test the feasibility of using automatic or semi-automatic methods to replace or reduce the intellectual effort involved in retrieving information from machine readable stores, particularly those using natural language. (Author)

Describes an experiment in automatic categorization, which is based on the vector model, widely used in information retrieval. Shows how the construction of the class patterns was carried out. Discusses the evaluation measures adopted and results obtained in the automatic categorization of a collection of documents in Spanish. Describes the manual…

Describes the design and implementation of a system for creating highlight abstracts to select relevant online magazine articles. Explains parsing texts based on text grammar and extracting sentences and statements that are relevant for inclusion in the abstract; and discusses knowledge representation and the importance of discourse structures in…