HiCuLR: Hierarchical Curriculum Learning for Rhetorical Role Labeling of Legal Documents

TL;DR

This paper introduces HiCuLR, a hierarchical curriculum learning framework that improves rhetorical role labeling in legal documents by systematically training models on varying difficulty levels at both document and role granularity.

Contribution

The paper proposes a novel hierarchical curriculum learning approach for RRL, combining document-level and role-level curricula to enhance model performance on legal texts.

Findings

HiCuLR outperforms existing methods on four RRL datasets.

Curriculum learning improves the model's ability to handle complex legal discourse.

Document difficulty metrics effectively guide the training process.

Abstract

Rhetorical Role Labeling (RRL) of legal documents is pivotal for various downstream tasks such as summarization, semantic case search and argument mining. Existing approaches often overlook the varying difficulty levels inherent in legal document discourse styles and rhetorical roles. In this work, we propose HiCuLR, a hierarchical curriculum learning framework for RRL. It nests two curricula: Rhetorical Role-level Curriculum (RC) on the outer layer and Document-level Curriculum (DC) on the inner layer. DC categorizes documents based on their difficulty, utilizing metrics like deviation from a standard discourse structure and exposes the model to them in an easy-to-difficult fashion. RC progressively strengthens the model to discern coarse-to-fine-grained distinctions between rhetorical roles. Our experiments on four RRL datasets demonstrate the efficacy of HiCuLR, highlighting the complementary nature of DC and RC.