TEAM: A Transportable Natural Language Interface System

Abstract

A major benefit of using natural language to access the information in a database is that it shifts onto the system the burden of mediating between two views of the data: the way in which the data is stored (the "database view"), and the way in which an end-user thinks about it (the "user*s view"). Database information is recorded in terms of files, records, and fields, while natural-language expressions refer to the same information in terms of entities and relationships in the world. A major problem in constructing a natural-language interface is determining how to encode and use the information needed to bridge these two views. Current natural-language interface systems require extensive efforts by specialists in natural-language processing to provide them with the information they need to do the bridging. The systems are, in effect, handtallored to provide access to particular databases. This paper focuses on the problem of constructing transportable natural-language interfaces, i.e., systems that can be adapted to provide access to databases for which they were not specifically handtailored. It describes an initial version of a transportable system, called TEAM (for ~ransportable E_ngllsh A_ccess Data manager). The hypothesis underlying the research described in this paper is that the information required for the adaptation can be obtained through an Lnteractlve dialogue with database management personnel who are not familiar with natural-language processing techniques.