Towards Grammatical Tagging for the Legal Language of Cybersecurity

TL;DR

This paper presents an automated methodology for Part of Speech tagging tailored to legal cybersecurity language, validated on EU legislation, highlighting limitations of existing NLP tools in this domain.

Contribution

It introduces a novel, adaptable POS tagging approach for legal cybersecurity texts, combining open-source NLP tools with manual validation.

Findings

Automated POS tagging methodology validated on EU cybersecurity legislation.

Existing NLP tools like SpaCy and ClausIE have limitations with legal cybersecurity language.

First structured interpretation of the NIS 2 cybersecurity directive.

Abstract

Legal language can be understood as the language typically used by those engaged in the legal profession and, as such, it may come both in spoken or written form. Recent legislation on cybersecurity obviously uses legal language in writing, thus inheriting all its interpretative complications due to the typical abundance of cases and sub-cases as well as to the general richness in detail. This paper faces the challenge of the essential interpretation of the legal language of cybersecurity, namely of the extraction of the essential Parts of Speech (POS) from the legal documents concerning cybersecurity. The challenge is overcome by our methodology for POS tagging of legal language. It leverages state-of-the-art open-source tools for Natural Language Processing (NLP) as well as manual analysis to validate the outcomes of the tools. As a result, the methodology is automated and, arguably, general for any legal language following minor tailoring of the preprocessing step. It is demonstrated over the most relevant EU legislation on cybersecurity, namely on the NIS 2 directive, producing the first, albeit essential, structured interpretation of such a relevant document. Moreover, our findings indicate that tools such as SpaCy and ClausIE reach their limits over the legal language of the NIS 2.