Ettore Mariotti

According to our database, Ettore Mariotti authored at least 7 papers between 2020 and 2024.

Collaborative distances:

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

2024

TextFocus: Assessing the Faithfulness of Feature Attribution Methods Explanations in Natural Language Processing.

Ettore Mariotti, Anna Arias-Duart, Michele Cafagna, Albert Gatt, Dario Garcia-Gasulla, Jose Maria Alonso-Moral

IEEE Access, 2024

2023

Exploring the balance between interpretability and performance with carefully designed constrainable Neural Additive Models.

Ettore Mariotti, Jose Maria Alonso-Moral, Albert Gatt

Inf. Fusion, November, 2023

Beyond Prediction Similarity: ShapGAP for Evaluating Faithful Surrogate Models in XAI.

Ettore Mariotti, Adarsa Sivaprasad, Jose Maria Alonso-Moral

Proceedings of the Explainable Artificial Intelligence, 2023

A Confusion Matrix for Evaluating Feature Attribution Methods.

Anna Arias-Duart, Ettore Mariotti, Dario Garcia-Gasulla, Jose Maria Alonso-Moral

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022

Measuring Model Understandability by means of Shapley Additive Explanations.

Ettore Mariotti, Jose Maria Alonso-Moral, Albert Gatt

Proceedings of the IEEE International Conference on Fuzzy Systems, 2022

2021

A Framework for Analyzing Fairness, Accountability, Transparency and Ethics: A Use-case in Banking Services.

Ettore Mariotti, José Maria Alonso, Roberto Confalonieri

Proceedings of the 30th IEEE International Conference on Fuzzy Systems, 2021

2020

Towards Harnessing Natural Language Generation to Explain Black-box Models.

Ettore Mariotti, José Maria Alonso, Albert Gatt

Proceedings of the 2nd Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence, 2020