In the last few years, we have been witnessing the increasing deployment of machine learning-based systems, which act as black boxes whose behaviour is hidden to end-users. As a side-effect, this contributes to increasing the need for explainable methods and tools to support the coordination between humans and ML models towards collaborative decision-making. In this paper, we demonstrate ContrXT, a novel tool that computes the differences in the classification logic of two distinct trained models, reasoning on their symbolic representation through Binary Decision Diagrams. ContrXT is available as a pip package and API.

Malandri, L., Mercorio, F., Mezzanzanica, M., Nobani, N., Seveso, A. (2022). The Good, the Bad, and the Explainer: A Tool for Contrastive Explanations of Text Classifiers. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence Demo Track. (pp.5936-5939). A A A I Press [10.24963/ijcai.2022/858].

The Good, the Bad, and the Explainer: A Tool for Contrastive Explanations of Text Classifiers

Malandri, Lorenzo;Mercorio, Fabio
;
Mezzanzanica, Mario;Nobani, Navid;Seveso, Andrea
2022

Abstract

In the last few years, we have been witnessing the increasing deployment of machine learning-based systems, which act as black boxes whose behaviour is hidden to end-users. As a side-effect, this contributes to increasing the need for explainable methods and tools to support the coordination between humans and ML models towards collaborative decision-making. In this paper, we demonstrate ContrXT, a novel tool that computes the differences in the classification logic of two distinct trained models, reasoning on their symbolic representation through Binary Decision Diagrams. ContrXT is available as a pip package and API.
paper
explainable AI; XAI; text classification; AI; machine learning
English
31st International Joint Conference on Artificial Intelligence, IJCAI 2022 - 23 July 2022 through 29 July 2022
2022
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence Demo Track.
978-1-956792-00-3
2022
5936
5939
none
Malandri, L., Mercorio, F., Mezzanzanica, M., Nobani, N., Seveso, A. (2022). The Good, the Bad, and the Explainer: A Tool for Contrastive Explanations of Text Classifiers. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence Demo Track. (pp.5936-5939). A A A I Press [10.24963/ijcai.2022/858].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/388786
Citazioni
  • Scopus 5
  • ???jsp.display-item.citation.isi??? ND
Social impact