Affordable Access

Publisher Website

An experimental study of natural language programming

Authors
Journal
International Journal of Man-Machine Studies
0020-7373
Publisher
Elsevier
Publication Date
Volume
18
Issue
1
Identifiers
DOI: 10.1016/s0020-7373(83)80005-4
Disciplines
  • Computer Science
  • Linguistics

Abstract

Abstract An experiment is described which gives data related to the usefulness and efficiency of English as a programming language. The experiment was performed with the NLC system, described herein, and used twenty-three paid volunteers from a first course in programming. Subjects were asked to solve two problems, namely (1) solution of linear equations and (2) gradebook averaging. A total of 1581 English sentences were typed, 81% of which were processed correctly. The remaining 19% were rejected because of questionable user syntax or system inadequacies. In most cases, subjects were able to paraphrase a rejected input in terminology understandable by the system. The overall success rate at solving an entire problem, within the 2½ h time constraint of the experiment, was 73·9%. In short, the system was an effective problem solver for the selected classes of problems and users. Many system failures resulted from “bugs” or syntactic oversights which appear amenable to easy repair. None of the Standard concerns about natural language programming related to vagueness, ambiguity, verbosity or correctness was a significant problem, although minor difficulties did arise occasionally.

There are no comments yet on this publication. Be the first to share your thoughts.