CoPERLex: Content Planning with Event-based Representations for Legal Case Summarization

2025-01-23

AI Summary

Legal judgment documents are excessively lengthy, hindering judges’ and lawyers’ rapid comprehension of case narrative logic. To address this, we propose a three-stage event-driven summarization framework: (1) extractive content selection; (2) event-structured planning based on subject–verb–object (SVO) triplets; and (3) plan-guided sequence-to-sequence summary generation. Diverging from dominant entity-centric paradigms, our work introduces the first event-centric legal summarization planning mechanism, explicitly modeling behavioral, agent, and patient relations to enhance factual consistency and interpretability. Evaluated on four legal summarization benchmarks, our method substantially outperforms strong baselines, achieving ROUGE-L improvements of 2.3–4.1 points. These results empirically validate the effectiveness of event-structured representations for modeling legal narratives.

Technology Category

• Natural Language Processing: Summarization
• Data Mining & Knowledge Management: Data Visualization & Summarization
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Legal professionals often struggle with lengthy judgments and require efficient summarization for quick comprehension. To address this challenge, we investigate the need for structured planning in legal case summarization, particularly through event-centric representations that reflect the narrative nature of legal case documents. We propose our framework, CoPERLex, which operates in three stages: first, it performs content selection to identify crucial information from the judgment; second, the selected content is utilized to generate intermediate plans through event-centric representations modeled as Subject-Verb-Object tuples; and finally, it generates coherent summaries based on both the content and the structured plan. Our experiments on four legal summarization datasets demonstrate the effectiveness of integrating content selection and planning components, highlighting the advantages of event-centric plans over traditional entity-centric approaches in the context of legal judgements.

Problem

• Legal Document Analysis
• Information Extraction
• Summary Generation

Innovation

• CoPERLex
• event-based legal case understanding
• abstract generation