USING RESTRICTED NATURAL LANGUAGE FOR DATA RETRIEVAL: A PLAN FOR FIELD EVALUATION

Abstract

One strategy that has been proposed for dealing with the growing backlog for development of applications is to give casual users languages for interacting directly with databases. Yet, there is little agreement on the form such languages should take. Should they be natural-like, conforming closely to a user's native tongue or should they be structured to take advantage of the characteristics of formal languages? This paper presents the rationale for and design of a field evaluation of natural language for data retrieval. The natural language system and application are described along with the research design of the project. The results of the first part of the study, a laboratory experiment to investigate whether users perform better with an artificial or natural language, suggest that after equal amounts of training no difference in subject performance is found between languages using a paper and pencil test . The insights gained to date are summarized.