Problems in Natural-Language Interface to DBMS With Examples From EUFID

PROBLEMS IN NATURAL-LANGUAGE INTERFACE TO DSMS WITH EXAMPLES FROM EUFID Marjorie Templeton John Burger System Development Corporation Santa Mortice, California ABSTRACT For five years the End-User Friendly Interface to Data management (EUFID) pro- ject team at System Development Corpora- tion worked on the design and implementa- tion of a Natural-Language Interface (NLI) system that was to be independent of both the application and the database management system. In this paper we describe application, natural-language and database management problems involved in NLI development, with specific refer- ence to the EUFID system as an example. I INTRODUCTION From 1976 to 1981 SDC was involved in the development of the End-User Friendly Interface to Data management (EUFID) system, a natural-language inter- face (NLI) that is designed to be independent of both the application and the underlying database management system (DBMS). [TEMP79, TEMP80, BURG80, BURG82]. The EUFID system permits users to communicate with database management systems in natural English rather than formal query languages. It is assumed that the application domain is well defined and bounded, that users share a common language to address the applica- tion, and that users may have little experience with computers or DBMSs but are competent in the application area. At least three broad categories of issues had to be addressed during EUFID development, and it is apparent that they are common to any general natural- language interface to database management systems. The first category involves the application: how to characterize the requirements of the human-machine dialo- gue and interaction, capture that infor- mation efficiently, formalize the infor- mation and incorporate that knowledge into a framework that can be used by the system. The major problems in this area are knowledge acquisition and representa- tion. For many NLI systems, bringing up a new application requires extensive effort by system designers with coopera- tion from a representative set of end- users. Tools that could assist in automating this process are badly needed. The second set of issues involves language processing techniques: how to assign constituent structure and interpretation to queries using robust and general methods that allow extension to additional lexical items, sentence types and semantic relationships. Some NLI systems distinguish the assignment of syntactic structure, or parsing, from the interpretation. Other systems, including EUFID, combine information about consti- tuent and semantic structure into an integrated semantic grammar. The third class involves database issues: how to actually perform the intent of the natural-language question by formulating the correct structured query and efficiently navigating through the database to retrieve the right answer. This involves a thorough under- standing of the DBMS structure underlying the application, the operations and func- tions the query language supports, and the nature and volatility of the data- base. Obviously issues in these three areas are related, and the knowledge needed to deal with them may be distri- buted throughout a natural-language interface system. The purpose of this paper is to show how such issues might be addressed in NLI development, with illus- trations from EUFID. The …

Content truncated to 500 words