Explaining Violation Traces with Finite State Natural Language Generation Models

TL;DR

This paper introduces a finite state natural language generation model designed to explain system violation traces, making technical deviations understandable at the business logic level through simplified, regular language explanations.

Contribution

The paper presents a novel finite state-based natural language generation approach for explaining violation traces at the business logic level.

Findings

The model effectively generates natural language explanations from violation traces.

It employs regular language transformations for abstraction and simplification.

The approach enhances user understanding of system deviations.

Abstract

An essential element of any verification technique is that of identifying and communicating to the user, system behaviour which leads to a deviation from the expected behaviour. Such behaviours are typically made available as long traces of system actions which would benefit from a natural language explanation of the trace and especially in the context of business logic level specifications. In this paper we present a natural language generation model which can be used to explain such traces. A key idea is that the explanation language is a CNL that is, formally speaking, regular language susceptible transformations that can be expressed with finite state machinery. At the same time it admits various forms of abstraction and simplification which contribute to the naturalness of explanations that are communicated to the user.