LEEC: A Legal Element Extraction Dataset with an Extensive Domain-Specific Label System

TL;DR

This paper introduces LEEC, a comprehensive large-scale dataset for legal element extraction in Chinese judicial documents, addressing limitations of previous datasets by providing extensive labels and legal domain specificity.

Contribution

The paper presents the creation of LEEC, the most extensive legal element extraction dataset for Chinese law, with expert-designed labels and validation using state-of-the-art models.

Findings

LEEC enables effective legal element extraction in Chinese judicial documents.

State-of-the-art models perform well on LEEC for document event extraction.

LEEC supports future research in legal NLP applications.

Abstract

As a pivotal task in natural language processing, element extraction has gained significance in the legal domain. Extracting legal elements from judicial documents helps enhance interpretative and analytical capacities of legal cases, and thereby facilitating a wide array of downstream applications in various domains of law. Yet existing element extraction datasets are limited by their restricted access to legal knowledge and insufficient coverage of labels. To address this shortfall, we introduce a more comprehensive, large-scale criminal element extraction dataset, comprising 15,831 judicial documents and 159 labels. This dataset was constructed through two main steps: first, designing the label system by our team of legal experts based on prior legal research which identified critical factors driving and processes generating sentencing outcomes in criminal cases; second, employing the legal knowledge to annotate judicial documents according to the label system and annotation guideline. The Legal Element ExtraCtion dataset (LEEC) represents the most extensive and domain-specific legal element extraction dataset for the Chinese legal system. Leveraging the annotated data, we employed various SOTA models that validates the applicability of LEEC for Document Event Extraction (DEE) task. The LEEC dataset is available on https://github.com/THUlawtech/LEEC .