Marco Sorbi

According to our database, Marco Sorbi authored at least 5 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2026

Probing Graph Neural Network Activation Patterns Through Graph Topology.

Floriano Tori, Lorenzo Bini, Marco Sorbi, Stéphane Marchand-Maillet, Vincent Ginis

CoRR, February, 2026

Weakly Supervised Named Entity Recognition for Historical Texts.

Marco Sorbi, Laurent Moccozet, Stéphane Marchand-Maillet

Proceedings of the 10th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, 2026

2025

Massive Activations in Graph Neural Networks: Decoding Attention dor Domain-Dependent Interpretability.

Lorenzo Bini, Marco Sorbi, Stéphane Marchand-Maillet

Proceedings of the Second Workshop on Second Workshop on Explainable Artificial Intelligence for the Medical Domain (EXPLIMED 2025) co-located with 28th European Conference on Artificial Intelligence (ECAI 2025), 2025

2024

Characterizing Massive Activations of Attention Mechanism in Graph Neural Networks.

Lorenzo Bini, Marco Sorbi, Stéphane Marchand-Maillet

CoRR, 2024

RCnum: A Semantic and Multilingual Online Edition of the Geneva Council Registers from 1545 to 1550.

Pierrette Bouillon, Christophe Chazalon, Sandra Coram-Mekkey, Gilles Falquet, Johanna Gerlach, Stéphane Marchand-Maillet, Laurent Moccozet, Jonathan Mutal, Raphael Rubino, Marco Sorbi

Proceedings of the 25th Annual Conference of the European Association for Machine Translation (Volume 2), 2024