In this paper, we cast Legal Judgment Prediction (LJP) from text on European Court of Human Rights cases as an entailment task, where the case outcome is classified from a combined input of case facts and convention articles. This configuration facilitates the model learning legal reasoning ability in mapping article text to specific fact text. It also provides the opportunity to evaluate the model's ability to generalize to zero-shot settings when asked to classify the case outcome with respect to articles not seen during training. We devise zero-shot LJP experiments and apply domain adaptation methods based on domain discriminator and Wasserstein distance. Our results demonstrate that the entailment architecture outperforms straightforward fact classification. We also find that domain adaptation methods improve zero-shot transfer performance, with article relatedness and encoder pre-training influencing the effect.

翻译：本文将欧洲人权法院案件文本的法律判决预测（LJP）构建为蕴含任务，即通过案件事实与公约条款的联合输入对案件结果进行分类。该配置有助于模型学习将条款文本映射至具体事实文本的法律推理能力。同时，当模型需对训练阶段未见条款进行案件结果分类时，该设置可评估其在零样本场景下的泛化能力。我们设计了零样本LJP实验，并采用基于领域判别器与Wasserstein距离的领域自适应方法。实验结果表明，蕴含架构优于直接的事实分类方法。此外，领域自适应方法能够提升零样本迁移性能，且条款关联性与编码器预训练对该效果具有影响。