A Note on Inforamtion Retrieval System

摘要

This paper is focused on the issues of automatic classification of Full-Text document. We give a model of developing a Classification Engine (CE) with the following aims : (1) To automate the classification procedure of INSPEC database (2) To achieve appropriate balance between specificity and exhaustivity, which are two important perspectives for the design of classification algorithms (3) To simplify retrieval operations so that users may find the query interface user-friendly. In particular, a user should not be expected to have specific knowledge about the topical domain in which the user seeks information for.