Structured method improves translating traffic rules into logic programs
Structured Four-Stage Legal Translation: From Natural-Language Traffic Rules to PROLOG
Artificial Intelligence
Summary
Traffic rules are written for people and often have vague language that computers find hard to understand exactly. The authors tested two ways to turn these rules into Prolog, a computer-friendly logical language, but both methods missed important details. They designed a new four-step process that breaks down the rules carefully, capturing meanings and exceptions better. This new way correctly translated more rules into clear logic that computers can use for reasoning about traffic laws.
What this means in practice
- •For legal technology developers: Create automated tools that convert traffic laws into precise logical rules for compliance checking and reasoning.
- •For road safety system designers: Integrate accurately formalized traffic rules into intelligent transportation systems to improve rule enforcement and decision making.
Authors
May Myo Zin, Wachara Fungwacharakorn, Ken Satoh, Katsumi Nitta
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 ($NL\rightarrow Prolog$) and Logical English to Prolog ($LE\rightarrow Prolog$), and introduces a new reasoning-guided translation framework called Structured Four-Stage Legal Translation ($S4L\rightarrow Prolog$). 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. $S4L\rightarrow Prolog$ achieves the highest accuracy, correctly formalizing 75 percent of the rules, while $NL\rightarrow Prolog$ reaches 60 percent and $LE\rightarrow Prolog$ 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.