Papers with RRL
Coupling Local Context and Global Semantic Prototypes via a Hierarchical Architecture for Rhetorical Roles Labeling (2026.eacl-long)
Copied to clipboard
Anas Belfathi, Nicolas Hernandez, Monceaux Laura, Warren Bonnard, Mary Catherine Lavissière, Christine Jacquin, Richard Dufour
| Challenge: | Hierarchical models capture local dependencies but lack global, corpus-level representations. |
| Approach: | They propose two prototype-based methods that integrate local context with global representations to address this limitation. |
| Outcome: | The proposed methods integrate local context with global representations. |
HiCuLR: Hierarchical Curriculum Learning for Rhetorical Role Labeling of Legal Documents (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches overlook the varying difficulty levels inherent in legal document discourse styles and rhetorical roles. |
| Approach: | They propose a hierarchical curriculum learning framework for RRL that nests two curricula: Rhetorical Role-level Curriculum (RC) on the outer layer and Document-level curriculum (DC) on inner layer. |
| Outcome: | The proposed framework is based on four legal document datasets and shows that it is complementary to existing models. |
Mind Your Neighbours: Leveraging Analogous Instances for Rhetorical Role Labeling for Legal Documents (2024.lrec-main)
Copied to clipboard
| Challenge: | Rhetorical Role Labeling (RRL) of legal judgments presents challenges such as inferring sentence roles from context, interrelated roles, limited annotated data, and label imbalance. |
| Approach: | They propose techniques to enhance RRL performance by leveraging knowledge from semantically similar instances. |
| Outcome: | The proposed methods achieve remarkable improvements in challenging macro-F1 scores. |