Zero-shot Transfer of Article-aware Legal Outcome Classification for European Court of Human Rights Cases

TL;DR

This paper introduces a zero-shot transfer approach for classifying European Court of Human Rights cases by integrating case facts and legal articles, enhancing legal reasoning and generalization to unseen articles.

Contribution

It presents an article-aware classification framework and domain adaptation techniques that improve zero-shot legal outcome prediction performance.

Findings

Article-aware architecture outperforms fact-only classification.

Domain adaptation methods enhance zero-shot transfer.

Pre-training and article relatedness influence results.

Abstract

In this paper, we cast Legal Judgment Prediction on European Court of Human Rights cases into an article-aware classification task, where the case outcome is classified from a combined input of case facts and convention articles. This configuration facilitates the model learning some legal reasoning ability in mapping article text to specific case fact text. It also provides an 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 experiments and apply domain adaptation methods based on domain discrimination and Wasserstein distance. Our results demonstrate that the article-aware 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.