Natural Language Approach Research Articles

A natural language approach to flexible model querying

Abstract We describe an interface to a crop model that uses techniques from natural language interpretation work. A graphical user interface (GUI) and a conventional command language each has its own limitations in terms of expressive power. Our restricted natural language interface (NLI) has some of the advantages of real natural language, such as familiarity of medium and tolerance of the user's manner of expression, together with some of the advantages of the GUI. Behind the interface itself, inferences are made with respect to the model, including query validity checking and disambiguation. In this paper we consider relevant prior research, before describing the project aims and details of the interface. We conclude with a discussion of the strengths and weaknesses of the approach taken, and how it could be improved.

Logical environment for natural language approach

Logical environment for natural language approach

Research into Expert Systems to Aid Simulation Model Formulation

The widespread availability of inexpensive computing power and recent developments in machine intelligence now makes it possible to consider computer assistance in the formulation phase of a discrete-event simulation model. The goal is to speed up this process. With this in mind, a series of prototype expert systems (written in LISP and run on an APPLE II) have been produced. The first prototype system was built using the ‘MYCIN’ approach. In the second prototype system a more informal approach was used, and the resulting computer-aided system is a natural-language understanding system. This paper outlines the need for such research and discusses the system development by describing the two main models and explaining why the natural-language approach was adopted.