Structured Four-Stage Legal Translation: From Natural-Language Traffic Rules to PROLOG

arXiv:2609.20334 · cs.AI · Submitted 2026-09-17 · Read on arXiv

cs.AI

Submitted: 2026-09-17

Updated: 2026-09-17

Comments: In Proceedings of the International Workshop on Translating Natural Legal Language into Formal Representations (NLL2FR 2025)

Code: https://github.com/mtproleg/NLL2FR2025

License: http://creativecommons.org/licenses/by/4.0/

The gist: Traffic regulations are written for human interpretation and therefore rely on shared background knowledge and flexible phrasing, which inherently introduce ambiguity, context dependence, and

Terminology

Abstract

Traffic regulations are written for human interpretation and therefore rely on shared background knowledge and flexible phrasing, which inherently introduce ambiguity, context dependence, and semantic underspecification. These linguistic characteristics conflict with the precision required by computational reasoning engines such as Prolog, which demand explicit logical structure. This study evaluates two baseline translation approaches, Natural Language to Prolog (NL to Prolog) and Logical English to Prolog (LE to Prolog), and introduces a new reasoning-guided translation framework called Structured Four-Stage Legal Translation (S4L to Prolog). The proposed S4L framework performs semantic role extraction, scene completion, logical mapping, and Prolog rule generation within a single guided prompt, enabling direct translation of raw traffic rules into executable logic without human intervention. A benchmark consisting of twenty real-world traffic rules was used to evaluate each approach in terms of syntactic validity, semantic correctness, and logical completeness. S4L to Prolog achieves the highest accuracy, correctly formalizing 75 percent of the rules, while NL to Prolog reaches 60 percent and LE to Prolog reaches 55 percent. Qualitative analysis further shows that S4L captures implicit causal relations, deontic modality, and exception structure more reliably than the baselines. These results demonstrate that structured reasoning prompts can substantially improve the reliability of natural-language-to-logic translation for legal and safety-critical applications.

Sources

Related papers