9 papers
Overcoming Copyright Barriers in Corpus Distribution Through Non-Reversible Hashing
Arthur Amalvy, Vincent Labatut, Xavier Bost +1
While annotated corpora are crucial in the field of natural language processing (NLP), those containing copyrighted material are difficult to exchange among researchers. Yet, such…
Persistent Homology of Topic Networks for the Prediction of Reader Curiosity
Manuel D. S. Hopp, Vincent Labatut, Arthur Amalvy +4
Reader curiosity, the drive to seek information, is crucial for textual engagement, yet remains relatively underexplored in NLP. Building on Loewenstein's Information Gap Theory, w…
Pattern-Based Graph Classification: Comparison of Quality Measures and Importance of Preprocessing
Lucas Potin, Rosa Figueiredo, Vincent Labatut +1
Graph classification aims to categorize graphs based on their structural and attribute features, with applications in diverse fields such as social network analysis and bioinformat…
Conversation-Based Multimodal Abuse Detection Through Text and Graph Embeddings
Noé Cecillon, Vincent Labatut, Richard Dufour
Abusive behavior is common on online social networks, and forces the hosts of such platforms to find new solutions to address this problem. Various methods have been proposed to au…
A Dataset of the Representatives Elected in France During the Fifth Republic
Noémie Févrat, Vincent Labatut, Ãmilie Volpi +1
The electoral system is a cornerstone of democracy, shaping the structure of political competition, representation, and accountability. In the case of France, it is difficult to ac…
FedSV: Byzantine-Robust Federated Learning via Shapley Value
Khaoula Otmani, Rachid Elazouzi, Vincent Labatut
In Federated Learning (FL), several clients jointly learn a machine learning model: each client maintains a local model for its local learning dataset, while a master server mainta…