A unifying similarity measure for automated identification of national implementations of european union directives

Abstract

is paper presents a unifying text similarity measure (USM) for automated identi cation of national implementations of European Union (EU) directives. e proposed model retrieves the transposed provisions of national law at a ne-grained level for each article of the directive. USM incorporates methods for matching common words, common sequences of words and approximate string matching. It was used for identifying transpositions on a multilingual corpus of four directives and their corresponding national implementing measures (NIMs) in three di erent languages : English, French and Italian. We further utilized a corpus of four additional directives and their corresponding NIMs in English language for a thorough test of the USM approach. We evaluated the model by comparing our results with a gold standard consisting of o cial correlation tables (where available) or correspondences manually identi ed by domain experts. Our results indicate that USM was able to identify transpositions with average F-score values of 0.808, 0.736 and 0.708 for French, Italian and English Directive-NIM pairs respectively in the multilingual corpus. A comparison with stateof-the-art methods for text similarity illustrates that USM achieves a higher F-score and recall across both the corpora.

Towards compliance checking in reified I/O logic via SHACL

“…Further directions of research include the automatic or semiautomatic generation of RDFs/OWL or SHACL assertions from legal texts, possibly via NLP (cf. [4], [5], [18]).…”

Assessing the Solid Protocol in Relation to Security and Privacy Obligations

“…In order to make this evolution feasible and effective from a practical point of view, we propose that such tables are published and maintained online thus allowing external contributors to also join the discussion and point out relevant literature and supporting documentation. In addition, they might be stored and visualised as semantically enriched hypertext that also employs AI to check consistency/completeness of the coverage of legal requirements (see [7,64] for the use of AI on similar use cases). The present paper can be a starting point for the creation of such an online repository and community.…”

An overview of information extraction techniques for legal document analysis and processing

“…Nanda et al [20] extended their work based unsupervised lexical and semantic similarity techniques [21], [22] to evaluate multilingual legal corpus of European directives and national legislation (from Ireland, Luxembourg, and Italy). They used shallow neural networks to developed word and paragraph embedding models for the corpus.…”