Automatic Extraction of Legal Norms: Evaluation of Natural Language Processing Tools

Abstract

Extracting and formalising legal norms from legal documents is a time-consuming and complex procedure. Therefore, the automatic methods that can accelerate this process are in high demand. In this paper, we address two major questions related to this problem: (i) what are the challenges in formalising legal documents into a machine understandable formalism? (ii) to what extent can the data-driven state-of-the-art approaches developed in the Natural Language Processing (NLP) community be used to automate the normative mining process. The results of our experiments indicate that NLP technologies such as relation extraction and semantic parsing are promising research avenues to advance research in this area.

Signal Phrase Extraction: A Gateway to Information Retrieval Improvement in Law Texts

“…In future works we plan to integrate our technique with several others, namely [13]. We also plan to enhance our framework by using EU legislative texts, which are published in all 24 official languages of the EU.…”

Reading Between the Lines: Information Extraction from Industry Requirements

“…A combination of deep semantic parsing and manual rules was used to identify normative clauses (obligations, permissions, prohibitions) from legal text by Dragoni et al (2016). Ferraro et al (2019) identify challenges when working with legal text and outlines a possible strategy for the automatic extraction of normative rules. In (Michel et al, 2022), the authors use FastText and a convolutional network to identify decision rules.…”

An End-to-End Pipeline from Law Text to Logical Formulas

“…Expressing laws computably is a classic objective of AI & Law [1] and a prerequisite to automating downstream tasks such as compliance checking [2], policy support [3], legislative simulation [4], and formal verification [3]. But faithfully translating law to logic is challenging [5], often requiring expertise in both legal and formal methods. This "natural language barrier" [6] poses a significant "knowledge bottleneck" [7] to computational law.…”

“…McCarty [6] used [11]'s statistical parser to extract from judicial opinions syntax trees then converted into semantic representations. [12] extract formal rules from deontically-and structurally-annotated legal texts with the standard NLP parsers, while [5] experiment with neural semantic parsing and open relation extraction.…”