A dependency-parsing method and a LEGAL-BERT-based classifier both reach roughly 80-84% accuracy for identifying regulatory statements in EU law on a new 7,200-sentence dataset, with a Krippendorff's alpha of 0.58 between them.
It is customary to require α ≥ .800 (for statistically significant reliability). Where tentative conclusions are still acceptable, α ≥ .667 is the lowest conceivable limit
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Computational Identification of Regulatory Statements in EU Legislation
A dependency-parsing method and a LEGAL-BERT-based classifier both reach roughly 80-84% accuracy for identifying regulatory statements in EU law on a new 7,200-sentence dataset, with a Krippendorff's alpha of 0.58 between them.