Explaining Violation Traces with Finite State Natural Language Generation Models
This work addresses the need for clearer communication of system deviations in verification, particularly for business logic specifications, though it appears incremental as it builds on existing finite state machinery and CNL approaches.
The paper tackles the problem of explaining violation traces in verification by presenting a natural language generation model that transforms long system action traces into natural language explanations, specifically using a controlled natural language (CNL) that is a regular language and allows for abstraction and simplification to enhance naturalness.
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.