Classifying proportionality - identification of a legal argument
Artificial Intelligence and Law · 2025-12 · 33 (4) · 1051-1078
DOI: 10.1007/s10506-024-09415-9 ↗Kurz gefasst
Fachartikel in der Zeitschrift Artificial Intelligence and Law, online erschienen am 03.08.2024. Verfasst von Kilian Lüders und 1 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deutsche Forschungsgemeinschaft, Humboldt-Universität zu Berlin.
Abstract (Originalsprache)
Proportionality is a central and globally spread argumentation technique in public law. This article provides a conceptual introduction to proportionality and argues that such a domain-specific form of argumentation is particularly interesting for argument mining. As a major contribution of this article, we share a new dataset for which proportionality has been annotated. The dataset consists of 300 German Federal Constitutional Court decisions annotated at the sentence level (54,929 sentences). In addition to separating textual parts, a fine-grained system of proportionality categories was used. Finally, we used these data for a classification task. We built classifiers that predict whether or not proportionality is invoked in a sentence. We employed several models, including neural and deep learning models and transformers. A BERT-BiLSTM-CRF model performed best.
Förderung
- Deutsche Forschungsgemeinschaft
- Humboldt-Universität zu Berlin
Zitieren
APA
Lüders, K., & Stohlmann, B. (2025). Classifying proportionality - identification of a legal argument. Artificial Intelligence and Law, 33(4), 1051-1078. https://doi.org/10.1007/s10506-024-09415-9
Vancouver
Lüders K, Stohlmann B. Classifying proportionality - identification of a legal argument. Artificial Intelligence and Law. 2025;33(4):1051-1078. doi:10.1007/s10506-024-09415-9
BibTeX
@article{Lders2025,
author = {Lüders, Kilian and Stohlmann, Bent},
title = {Classifying proportionality - identification of a legal argument},
journal = {Artificial Intelligence and Law},
year = {2025},
volume = {33},
number = {4},
pages = {1051--1078},
doi = {10.1007/s10506-024-09415-9}
}
EUVIMED