DC-D1-LegalBERT v1: Deference Classifier — Rights Framing
Fine-tuned from nlpaueb/legal-bert-base-uncased for 4-class classification of ECtHR paragraphs
on deference dimension D1 (Rights Framing).
Classes: ND (0) | MD (1) | HD (2) | NA (3)
Scoring rule: continuous deference score = 0×p(ND) + 0.5×p(MD) + 1.0×p(HD);
NaN if p(NA) is argmax.
Training data snapshot (v1)
- Train paragraphs : 588
- Val paragraphs : 126
Validation performance (v1)
- Best macro-F1 : 0.7245
- Mean macro-F1 : 0.5732 ± 0.1839
- All seeds : [0.6252, 0.6719, 0.7245, 0.2123, 0.632]
Training setup
- Regime : small (10 epochs, batch size 8, 5 seeds)
- Learning rate : 2e-05
- Seeds tested : [0, 1, 2, 3, 4]
Intended use
Part of a Master's Thesis measuring judicial deference in ECtHR Article 8 migration cases.
Not intended for production use.
