An automated framework for the extraction of semantic legal metadata from legal texts

Abstract

Semantic legal metadata provides information that helps with understanding and interpreting legal provisions. Such metadata is therefore important for the systematic analysis of legal requirements. However, manually enhancing a large legal corpus with semantic metadata is prohibitively expensive. Our work is motivated by two observations: (1) the existing requirements engineering (RE) literature does not provide a harmonized view on the semantic metadata types that are useful for legal requirements analysis; (2) automated support for the extraction of semantic legal metadata is scarce, and it does not exploit the full potential of artificial intelligence technologies, notably natural language processing (NLP) and machine learning (ML). Our objective is to take steps toward overcoming these limitations. To do so, we review and reconcile the semantic legal metadata types proposed in the RE literature. Subsequently, we devise an automated extraction approach for the identified metadata types using NLP and ML. We evaluate our approach through two case studies over the Luxembourgish legislation. Our results indicate a high accuracy in the generation of metadata annotations. In particular, in the two case studies, we were able to obtain precision scores of 97.2% and 82.4%, and recall scores of 94.9% and 92.4%.

Automatic Semantic Annotation of News Images in Mobile Internet of Things and Construction of Semantic Internet of Things System

“…The texture feature of an image describes the arrangement of the components of each object in the image, and it is a periodically changing visual element. There are three commonly used texture feature extraction methods, which are statistics-based texture feature extraction method, signal processing-based texture feature extraction method, and structure-based feature extraction method [17][18][19][20]. The research object of the texture feature extraction method based on statistics is the gray value of the current pixel, and the extracted texture feature is the first or higher derivative statistical information of gray.…”

Vision for an Artefact-based Approach to Regulatory Requirements Engineering

“…Existing regulatory RE methods for addressing regulatory norms and requirements at a semantic level do seldom consider the peculiar nature of legal norms. Semantic analysis methods (e.g., [5,31]) assume that it is possible to derive requirements from the regulations' immediate analysis (e.g., using an upper ontology [5] or semantic metadata [31]). However, legal scholarship provides a different perspective on the nature of regulatory norms and their meaning, as discussed next.…”

“…Previous research in linguistics found that the language of law is characterized by specific rules of entailment, dependent on its syntactic structures [20]. Previous regulatory RE research has paid attention to concepts that can be used for the semantic analysis of regulations (e.g., as a part of an upper-ontology [5] or as a system of semantic metadata concepts [31]). It is widely accepted that regulatory norms are expressed in the form of rights and obligations [31].…”

“…Previous regulatory RE research has paid attention to concepts that can be used for the semantic analysis of regulations (e.g., as a part of an upper-ontology [5] or as a system of semantic metadata concepts [31]). It is widely accepted that regulatory norms are expressed in the form of rights and obligations [31]. In our opinion, rights and obligations can also be considered as an element type of the structure of regulations or, in other words, regulatory syntactic categories.…”

“…Nevertheless, some challenges remain unresolved as there is still a "gap between engineers and legal experts" [9]. In research that considers the automatic processing of regulatory acts without legal experts' involvement, there is no agreement about the semantic concepts that can be automatically extracted from regulatory acts [10]. Available studies corroborate that engineering-legal interactions are challenging [11] because of the differences in language and terminology [11], the simplistic perception of each domain in regulatory RE [4], [12], and the implicit nature of legal knowledge during the interaction [13].…”