Mind Your Neighbours: Leveraging Analogous Instances for Rhetorical Role Labeling for Legal Documents

TL;DR

This paper proposes novel inference and training techniques leveraging similar instances to improve rhetorical role labeling in legal documents, addressing challenges like limited data and label imbalance, with cross-domain applicability.

Contribution

It introduces knowledge transfer methods using neighbors, including interpolation and prototypical learning with contrastive techniques, enhancing RRL performance in legal texts.

Findings

Significant macro-F1 score improvements in RRL tasks.

Effective cross-domain transfer of methods across legal areas.

Demonstrated robustness of techniques without extensive retraining.

Abstract

Rhetorical Role Labeling (RRL) of legal judgments is essential for various tasks, such as case summarization, semantic search and argument mining. However, it presents challenges such as inferring sentence roles from context, interrelated roles, limited annotated data, and label imbalance. This study introduces novel techniques to enhance RRL performance by leveraging knowledge from semantically similar instances (neighbours). We explore inference-based and training-based approaches, achieving remarkable improvements in challenging macro-F1 scores. For inference-based methods, we explore interpolation techniques that bolster label predictions without re-training. While in training-based methods, we integrate prototypical learning with our novel discourse-aware contrastive method that work directly on embedding spaces. Additionally, we assess the cross-domain applicability of our methods, demonstrating their effectiveness in transferring knowledge across diverse legal domains.