Knowledge-based machine indexing from natural language text: Knowledge base design, development, and maintenance

摘要

One strategy for machine-aided indexing (MAI) is to provide a concept-level analysis of the textual elements of documents or document abstracts. In such systems, natural-language phrases are analyzed in order to identify and classify concepts related to a particular subject domain. The overall performance of these MAI systems is largely dependent on the quality and comprehensiveness of their knowledge bases. These knowledge bases function to (1) define the relations between a controlled indexing vocabulary and natural language expressions; (2) provide a simple mechanism for disambiguation and the determination of relevancy; and (3) allow the extension of concept-hierarchical structure to all elements of the knowledge file. After a brief description of the NASA Machine-Aided Indexing system, concerns related to the development and maintenance of MAI knowledge bases are discussed. Particular emphasis is given to statistically-based text analysis tools designed to aid the knowledge base developer. One such tool, the Knowledge Base Building (KBB) program, presents the domain expert with a well-filtered list of synonyms and conceptually-related phrases for each thesaurus concept. Another tool, the Knowledge Base Maintenance (KBM) program, functions to identify areas of the knowledge base affected by changes in the conceptual domain (for example, the addition of a new thesaurus term). An alternate use of the KBM as an aid in thesaurus construction is also discussed.