Automated Extraction of Sentencing Decisions from Court Cases in the Hebrew Language

TL;DR

This paper introduces Automated Punishment Extraction (APE) from Hebrew court cases, creating datasets and models to identify sentencing decisions, which aids legal NLP applications and understanding sentencing patterns.

Contribution

It presents the first dataset and benchmark models for APE in Hebrew court cases, comparing rule-based and supervised approaches, and analyzing sentencing patterns.

Findings

Supervised models accurately identify punishment sentences.

Rule-based approaches outperform supervised models on full APE task.

Analysis reveals common errors and future directions for distinguishing punishment types.

Abstract

We present the task of Automated Punishment Extraction (APE) in sentencing decisions from criminal court cases in Hebrew. Addressing APE will enable the identification of sentencing patterns and constitute an important stepping stone for many follow up legal NLP applications in Hebrew, including the prediction of sentencing decisions. We curate a dataset of sexual assault sentencing decisions and a manually-annotated evaluation dataset, and implement rule-based and supervised models. We find that while supervised models can identify the sentence containing the punishment with good accuracy, rule-based approaches outperform them on the full APE task. We conclude by presenting a first analysis of sentencing patterns in our dataset and analyze common models' errors, indicating avenues for future work, such as distinguishing between probation and actual imprisonment punishment. We will make all our resources available upon request, including data, annotation, and first benchmark models.