Incorporating Domain Knowledge for Extractive Summarization of Legal Case Documents

TL;DR

This paper introduces DELSumm, an unsupervised legal document summarization method that integrates expert guidelines, outperforming existing algorithms including supervised models on Indian Supreme Court case documents.

Contribution

The paper presents DELSumm, a novel unsupervised algorithm that systematically incorporates legal domain knowledge into extractive summarization.

Findings

Outperforms strong baselines in ROUGE scores

Surpasses supervised models trained on large datasets

Effective on Indian Supreme Court case documents

Abstract

Automatic summarization of legal case documents is an important and practical challenge. Apart from many domain-independent text summarization algorithms that can be used for this purpose, several algorithms have been developed specifically for summarizing legal case documents. However, most of the existing algorithms do not systematically incorporate domain knowledge that specifies what information should ideally be present in a legal case document summary. To address this gap, we propose an unsupervised summarization algorithm DELSumm which is designed to systematically incorporate guidelines from legal experts into an optimization setup. We conduct detailed experiments over case documents from the Indian Supreme Court. The experiments show that our proposed unsupervised method outperforms several strong baselines in terms of ROUGE scores, including both general summarization algorithms and legal-specific ones. In fact, though our proposed algorithm is unsupervised, it outperforms several supervised summarization models that are trained over thousands of document-summary pairs.