The recent growth of black-box machine-learning methods in data analysis has increased the demand for explanation methods and tools to understand their behaviour and assist human-ML model cooperation. In this paper, we demonstrate ContrXT, a novel approach that uses natural language explanations to help users to comprehend how a back-box model works. ContrXT provides time contrastive (t-contrast) explanations by computing the differences in the classification logic of two different trained models and then reasoning on their symbolic representations through Binary Decision Diagrams. ContrXT is publicly available at ContrXT.ai as a python pip package.

Malandri, L., Mercorio, F., Mezzanzanica, M., Nobani, N., Seveso, A. (2022). Contrastive Explanations of Text Classifiers as a Service. In NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Demonstrations Session (pp.46-53) [10.18653/v1/2022.naacl-demo.6].

Contrastive Explanations of Text Classifiers as a Service

Malandri L.;Mercorio F.;Mezzanzanica M.;Nobani N.;Seveso A.
2022

Abstract

The recent growth of black-box machine-learning methods in data analysis has increased the demand for explanation methods and tools to understand their behaviour and assist human-ML model cooperation. In this paper, we demonstrate ContrXT, a novel approach that uses natural language explanations to help users to comprehend how a back-box model works. ContrXT provides time contrastive (t-contrast) explanations by computing the differences in the classification logic of two different trained models and then reasoning on their symbolic representations through Binary Decision Diagrams. ContrXT is publicly available at ContrXT.ai as a python pip package.
paper
xai; machine learning
English
2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022 - 10 July 2022through 15 July 2022
2022
NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Demonstrations Session
9781955917742
2022
46
53
open
Malandri, L., Mercorio, F., Mezzanzanica, M., Nobani, N., Seveso, A. (2022). Contrastive Explanations of Text Classifiers as a Service. In NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Demonstrations Session (pp.46-53) [10.18653/v1/2022.naacl-demo.6].
File in questo prodotto:
File Dimensione Formato  
10281-396956_VoR.pdf

accesso aperto

Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Licenza: Creative Commons
Dimensione 1.14 MB
Formato Adobe PDF
1.14 MB Adobe PDF Visualizza/Apri

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/10281/396956
Citazioni
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 1
Social impact