Abstract
This paper describes the design of a transportable natural language (NL) interface to databases and the constraints that transportability places on each components of such a system. By a transportable NL system, we mean an NL processing system that is constructed so that a domain expert (rather than an AI or linguistics expert) can move the system to a new application domain. After discussing the general problems presented by transportability, this paper describes TEAM (an acronym for Transportable English database Access Medium), a demonstratable prototype of such a system. The discussion of TEAM shows how domain-independent and domain-dependent information can be separated in the different components of an NL interface system, and presents one method of obtaining domain-specific information from a domain expert.
Share this
