Natural Language Access to Databases: Interpreting Update Requests
Abstract
For natural language database systems to operate effectively in practical domains, they must have the capabilities required by real applications. One such capability is understanding and performing update requests. The processing of natural language updates raises problems not encountered in the processing of queries. These difficulties stem from the fact that the user will naturally phrase requests with respect to his conception of the domain, which may be a considerable simplification of the actual underlying database structure. Updates which are meaningful and unambiguous from the user's standpoint may not translate into reasonable changes to the underlying database. Update requests may be impossible (cannot be performed in any way), ambiguous (can be performed in several ways), or pathological (can be performed only in ways which cause undesirable side effects). Drawing on work in Linguistics and Philosophy of Language, we have developed a domain-transparent approach to identifying and performing 'reasonable' changes in response to a user's update request, using only knowledge sources typically present in existing database systems. A simple notion of 'user model' and explanation with respect to the user's state of knowledge are central to the design. This paper describes a system PIQUE (Program for Interpreatation of Query/Update in English), which implements this approach. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Sep 30, 1981
- Accession Number
- ADA109183
Entities
People
- J. L. Davidson
- S. Jerrold Kaplan
Organizations
- Stanford University