Normalization of titles and their retrieval

摘要

This paper presents a method of normalizations of English titles and their retrieval. The title expressed by a noun phrase or a noun clause is converted to a function-expression by parsing. For the retrieval with a reasonable recall rate as well as a high precision rate, the function-expression is transformed to a predicate-governor form, and then normalized to a standard form. Therefrom, various items are extracted and recorded in a hierarchical tree-like inverted file.In order to keep the recall rate in a reasonable value, several retrieval stages are implemented based on the key-term and case-label matching. The retrieval is controlled by the preciseness of the specification of case-labels for each key-term.