The task of producing satisfactory indexes by automatic means has been tackled on two fronts: by statistical analysis of text and by attempting content analysis of the text in much the same way as a human indexcr does. Though statistical techniques have a lot to offer for free-text database systems, neither method has had much success with back-of-the-bopk indexing. This review examines some problems associated with the application of natural-language processing techniques to book texts.
No takes yet. Share an insight, caveat, or question.
Korycinski et al. (1990) studied this question.
Synapse has enriched 5 related papers. Consider them for comparative context: