PBS: An economical natural language query interpreter

✍ Scribed by Samstag-Schnock, Uwe ;Meadow, Charles T.

• Publisher: John Wiley and Sons
• Year: 1993
• Tongue: English
• Weight: 902 KB
• Volume: 44
• Category: Article
• ISSN: 0002-8231
• DOI: 10.1002/(sici)1097-4571(199306)44:5<265::aid-asi2>3.0.co;2-v

✦ Synopsis

A natural language interface, named PBS, to a bibliographic information retrieval system, is described, which receives natural language search statements from an end-user and identifies search facets and implied Boolean logic operators. The program is intended for use in conjunction with an intermediary program (OAK) for online database searching, operating in a user's personal computer. Such a program must be fast and make minimal demands on memory, which places severe restrictions on storage of dictionaries and thesauri needed for full natural language interpretation. This initial version deals with a single domain, bibliographic files, almost all of which use the same attributes, such as subject, author, or journal name. The objective of PBS is to identify terms in a natural language query, classify them by attribute, recognize the boolean logic stated or implied, conflate terms that have minor spelling variations, and present the terms to the intermediary program, organized by facet or term category. In testing, the main difficulty resulted from false identification of journal names. Yet, in light of the editorial capabilities of OAK, which allow a user to correct a query before It is given to an IRS, PBS can be regarded as a workable natural language interface that can alleviate some of the problems inherent in native command languages.