Developing controlled natural language for formal specification patterns using AI assistants

TL;DR

This paper presents a method leveraging AI assistants to systematically develop controlled natural language for formal specifications, focusing on requirements with logical attributes, tested on event-driven temporal requirements.

Contribution

It introduces a three-stage approach for constructing controlled natural language from formal specification patterns using AI, enhancing precision and consistency.

Findings

Successfully applied to event-driven temporal requirements

Generated a comprehensive corpus of natural language patterns

Formalized the syntax of the controlled language

Abstract

Using an AI assistant, we developed a method for systematically constructing controlled natural language for requirements based on formal specification patterns containing logical attributes. The method involves three stages: 1) compiling a generalized natural language requirement pattern that utilizes all attributes of the formal specification template; 2) generating, using the AI assistant, a corpus of natural language requirement patterns, reduced by partially evaluating attributes (the developed prompt utilizes the generalized template, attribute definitions, and specific formal semantics of the requirement patterns); and 3) formalizing the syntax of the controlled natural language based on an analysis of the grammatical structure of the resulting patterns. The method has been tested for event-driven temporal requirements.