A Comprehensive Survey on Legal Summarization: Challenges and Future Directions

TL;DR

This survey comprehensively reviews recent advances in legal text summarization, highlighting current techniques, datasets, challenges, and future research directions in the NLP legal domain.

Contribution

It provides the first systematic review of legal summarization methods, covering over 120 papers and focusing on transformer-based models and evaluation strategies.

Findings

Transformer models dominate legal summarization research.

Legal datasets are limited and need standardization.

Significant challenges remain in model explainability and dataset diversity.

Abstract

This article provides a systematic up-to-date survey of automatic summarization techniques, datasets, models, and evaluation methods in the legal domain. Through specific source selection criteria, we thoroughly review over 120 papers spanning the modern `transformer' era of natural language processing (NLP), thus filling a gap in existing systematic surveys on the matter. We present existing research along several axes and discuss trends, challenges, and opportunities for future research.