A Hierarchical Label Network for Multi-label EuroVoc Classification of Legislative Contents

Explainable machine learning multi-label classification of Spanish legal judgements

“…Transformation and adaptation approaches can rely on diverse general strategies, such as one-vs-all (Sengupta & Dave, 2021), tree ensembles (Moyano et al, 2018), embedding solutions (Caled et al, 2022(Caled et al, , 2019 and deep learning (Caled et al, 2022). The training and testing processes of the one-vs-all strategy are computationally consuming, however.…”

“…We remark that there exists research on the classification of other types of legal documents outside the scope of this work. Both Sengupta & Dave (2021) and Caled et al (2022Caled et al ( , 2019 focused on legislative texts. These are substantially different to court judgements and require specific methodologies.…”

Hierarchical Text Classification and Its Foundations: A Review of Current Research

“…Thus, thanks to the increased availability of TC datasets that integrate hierarchical structure in their labels, as well as a general interest in industrial applications that utilize TC, a large number of new methods for HTC have been proposed in recent years. Indeed, HTC has many practical applications beyond classic TC, such as International Classification of Diseases (ICD) medical coding [5,6], legal document concept labeling [7], patent labeling [8], IT ticket classification [9], and more.…”

“…Secondly, errors in the upper levels of the hierarchy are inherently worse (e.g., misclassifying "football" as "rugby" is comparatively better than misclassifying "sport" as "food"). These considerations also make sense when considering real-world applications of HTC, such as ICD coding [5,6] and legal document concept labeling [7]. A better mistake entails that most ancestor nodes in the prediction path were correct, meaning that most of the macro categorizations of the sample were accurate.…”

Facilitating access to data on European Union laws

“…Lampach, Wijtvliet, and Dyevre 2020;Marciano and Josselin 2002) to computational linguistics (e.g. Caled et al 2019;Chalkidis et al 2019;Quaresma and Gonçalves 2010), data on EU laws and policy documents represent core empirical material for the study of European integration. Although usually each study comes with its own bespoke dataset, the data is frequently collected from the same source, the Eur-Lex website, 1 which aggregates documents from EU institutions (Düro 2009;Bernet and Berteloot 2006).…”