Coupling Local Context and Global Semantic Prototypes via a Hierarchical Architecture for Rhetorical Roles Labeling

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Belfathi, Anas, Hernandez, Nicolas, Monceaux, Laura, Bonnard, Warren, Lavissiere, Mary Catherine, Jacquin, Christine, Dufour, Richard
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914368194609152
author Belfathi, Anas
Hernandez, Nicolas
Monceaux, Laura
Bonnard, Warren
Lavissiere, Mary Catherine
Jacquin, Christine
Dufour, Richard
author_facet Belfathi, Anas
Hernandez, Nicolas
Monceaux, Laura
Bonnard, Warren
Lavissiere, Mary Catherine
Jacquin, Christine
Dufour, Richard
contents Rhetorical Role Labeling (RRL) identifies the functional role of each sentence in a document, a key task for discourse understanding in domains such as law and medicine. While hierarchical models capture local dependencies effectively, they are limited in modeling global, corpus-level features. To address this limitation, we propose two prototype-based methods that integrate local context with global representations. Prototype-Based Regularization (PBR) learns soft prototypes through a distance-based auxiliary loss to structure the latent space, while Prototype-Conditioned Modulation (PCM) constructs corpus-level prototypes and injects them during training and inference. Given the scarcity of RRL resources, we introduce SCOTUS-Law, the first dataset of U.S. Supreme Court opinions annotated with rhetorical roles at three levels of granularity: category, rhetorical function, and step. Experiments on legal, medical, and scientific benchmarks show consistent improvements over strong baselines, with 4 Macro-F1 gains on low-frequency roles. We further analyze the implications in the era of Large Language Models and complement our findings with expert evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2603_03856
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Coupling Local Context and Global Semantic Prototypes via a Hierarchical Architecture for Rhetorical Roles Labeling
Belfathi, Anas
Hernandez, Nicolas
Monceaux, Laura
Bonnard, Warren
Lavissiere, Mary Catherine
Jacquin, Christine
Dufour, Richard
Computation and Language
Rhetorical Role Labeling (RRL) identifies the functional role of each sentence in a document, a key task for discourse understanding in domains such as law and medicine. While hierarchical models capture local dependencies effectively, they are limited in modeling global, corpus-level features. To address this limitation, we propose two prototype-based methods that integrate local context with global representations. Prototype-Based Regularization (PBR) learns soft prototypes through a distance-based auxiliary loss to structure the latent space, while Prototype-Conditioned Modulation (PCM) constructs corpus-level prototypes and injects them during training and inference. Given the scarcity of RRL resources, we introduce SCOTUS-Law, the first dataset of U.S. Supreme Court opinions annotated with rhetorical roles at three levels of granularity: category, rhetorical function, and step. Experiments on legal, medical, and scientific benchmarks show consistent improvements over strong baselines, with 4 Macro-F1 gains on low-frequency roles. We further analyze the implications in the era of Large Language Models and complement our findings with expert evaluation.
title Coupling Local Context and Global Semantic Prototypes via a Hierarchical Architecture for Rhetorical Roles Labeling
topic Computation and Language
url https://arxiv.org/abs/2603.03856