Recently, Logic Explained Networks (LENs) have been proposed as explainable-by-design neural models providing logic explanations for their predictions. However, these models have only been applied to vision and tabular data, and they mostly favour the generation of global explanations, while local ones tend to be noisy and verbose. For these reasons, we propose LENp, improving local explanations by perturbing input words, and we test it on text classification. Our results show that (i) LENp provides better local explanations than LIME in terms of sensitivity and faithfulness, and (ii) logic explanations are more useful and user-friendly than feature scoring provided by LIME as attested by a human survey.

Extending logic explained networks to text classification

Giannini, Francesco;Lio, Pietro
2022

Abstract

Recently, Logic Explained Networks (LENs) have been proposed as explainable-by-design neural models providing logic explanations for their predictions. However, these models have only been applied to vision and tabular data, and they mostly favour the generation of global explanations, while local ones tend to be noisy and verbose. For these reasons, we propose LENp, improving local explanations by perturbing input words, and we test it on text classification. Our results show that (i) LENp provides better local explanations than LIME in terms of sensitivity and faithfulness, and (ii) logic explanations are more useful and user-friendly than feature scoring provided by LIME as attested by a human survey.
2022
Settore IINF-05/A - Sistemi di elaborazione delle informazioni
Settore INFO-01/A - Informatica
2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
are
2022
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
Association for Computational Linguistics (ACL)
File in questo prodotto:
File Dimensione Formato  
EMNLP 2022 - Extending Logic Explained Networks to Text Classification.pdf

accesso aperto

Tipologia: Published version
Licenza: Solo Lettura
Dimensione 779.18 kB
Formato Adobe PDF
779.18 kB Adobe PDF

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/11384/150602
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 6
  • ???jsp.display-item.citation.isi??? ND
  • OpenAlex ND
social impact