1 citations · 1 across the 4 of their papers we have counts for
4 papers · 1 filter
Semantic Reranking at Inference Time for Hard Examples in Rhetorical Role Labeling
Anas Belfathi, Nicolas Hernandez, Laura Monceaux +2
Rhetorical Role Labeling (RRL) assigns a functional role to each sentence in a document and is widely used in legal, medical, and scientific domains. While language models (LMs) ac…
Coupling Local Context and Global Semantic Prototypes via a Hierarchical Architecture for Rhetorical Roles Labeling
Anas Belfathi, Nicolas Hernandez, Laura Monceaux +4
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 hier…
Language Model Adaptation to Specialized Domains through Selective Masking based on Genre and Topical Characteristics
Anas Belfathi, Ygor Gallina, Nicolas Hernandez +2
Recent advances in pre-trained language modeling have facilitated significant progress across various natural language processing (NLP) tasks. Word masking during model training co…
Harnessing GPT-3.5-turbo for Rhetorical Role Prediction in Legal Cases
Anas Belfathi, Nicolas Hernandez, Laura Monceaux
We propose a comprehensive study of one-stage elicitation techniques for querying a large pre-trained generative transformer (GPT-3.5-turbo) in the rhetorical role prediction task…