Developing a natural language interface to complex data

Abstract

Aspects of an intelligent interface that provides natural language access to a large body of data distributed over a computer network are described. The overall system architecture is presented, showing how a user is buffered from the actual database management systems (DBMSs) by three layers of insulating components. These layers operate in series to convert natural language queries into calls to DBMSs at remote sites. Attention is then focused on the first of the insulating components, the natural language system. A pragmatic approach to language access that has proved useful for building interfaces to databases is described and illustrated by examples. Special language features that increase system usability, such as spelling correction, processing of incomplete inputs, and run-time system personalization, are also discussed. The language system is contrasted with other work in applied natural language processing, and the system's limitations are analyzed.

A tool for access to relational databases in natural language

“…It proved ineffective because it was very specialized. The LADDER (Hendrix, Sacerdoti, Sagalowicz, & Slocum, 1978) was the first system to include grammar analysis, communicating with a database that contains information concerning the US navy ships. The most familiar example of database interaction system in natural language is the CHAT-80 (Warren & Pereira, 1982).…”

A natural language help system shell through functional programming

“…However, a pre-requisite factor on the nature and form of the data structure is the language with which the whole system is to be implemented. There is a wide choice of languages with which the implementation could be performed: † Procedural (imperative) languages such as Pascal [26,27], C [28], Perl [29] † Specialist languages for NLP such as LIFER [10]. † Assumptive Logic Programming [30], † Object languages such as Visual Basic [31], Objectorientated Languages such as Cþþ [32], Java [33] and Smalltalk [34] † Traditional artificial intelligence languages of Prolog [35,36] (Clive, 1998) and Lisp [37,38].…”

Query languages for statistical databases

“…Examples are SIR/ DBMS (Anderson et al 1983), TPL and TPLDCS (Weiss et al 1981) and BROWSE (Hendrix et al 1978).…”