# Neural Legal Judgment Prediction in English

## TL;DR

This paper introduces a new English legal judgment prediction dataset from the European Court of Human Rights, evaluates neural models on it, and proposes a hierarchical BERT variant to handle long texts.

## Contribution

It provides the first English dataset for legal judgment prediction, benchmarks neural models, and introduces a hierarchical BERT to address length limitations.

## Key findings

- Neural models outperform feature-based approaches on the new dataset.
- Models can predict case outcomes with high accuracy across tasks.
- Hierarchical BERT effectively processes long legal texts.

## Abstract

Legal judgment prediction is the task of automatically predicting the outcome of a court case, given a text describing the case's facts. Previous work on using neural models for this task has focused on Chinese; only feature-based models (e.g., using bags of words and topics) have been considered in English. We release a new English legal judgment prediction dataset, containing cases from the European Court of Human Rights. We evaluate a broad variety of neural models on the new dataset, establishing strong baselines that surpass previous feature-based models in three tasks: (1) binary violation classification; (2) multi-label classification; (3) case importance prediction. We also explore if models are biased towards demographic information via data anonymization. As a side-product, we propose a hierarchical version of BERT, which bypasses BERT's length limitation.