Legal Search in Case Law and Statute Law

TL;DR

This paper presents a method for legal document relevance ranking that leverages text summaries and generalized language models, outperforming full-text baselines in resource-constrained legal collections.

Contribution

It introduces a novel approach using summaries with language models for legal relevance, demonstrating improved performance over traditional full-text methods.

Findings

Summaries enhance relevance detection accuracy.

Language models outperform traditional baselines.

Potential for future improvements in legal search.

Abstract

In this work we describe a method to identify document pairwise relevance in the context of a typical legal document collection: limited resources, long queries and long documents. We review the usage of generalized language models, including supervised and unsupervised learning. We observe how our method, while using text summaries, overperforms existing baselines based on full text, and motivate potential improvement directions for future work.