A Proposal of a Language-Based Context-Sensitive Programming System

This paper describes a programming system with which even novice users can easily specify complex requests as natural language texts, in other words, write programs in everyday language, to operate computing systems. Based on a study of task specification texts written by non-programmers, the processing model is designed so that implicit and ambiguous information in an input text is detected and transformed into an explicit executable program structure. Context dependency in programming is also considered. Context-dependent factors in the situation of program development and the situation of program execution are considered in text understanding and program execution phases, bridging the gap between these two contexts. We have developed a prototype system that deals with personal email management tasks. In this paper, we explain our processing model, give evaluation results, and discuss our proposal’s effectiveness and projected work.