In this paper, we present a post-hoc method to produce highly interpretable global rules to explain NLP classifiers. Rules are extracted with a data mining approach on a semantically enriched input representation, instead of using words/wordpieces solely. Semantic information yields more abstract and general rules that are both more explanatory and less complex, while being also better at reflecting the model behaviour.

Zugarini, A., Rigutini, L. (2023). SAGE: Semantic-Aware Global Explanations for Named Entity Recognition. In 2023 International Joint Conference on Neural Networks (IJCNN) Proceedings (pp.1-8). New York : IEEE [10.1109/IJCNN54540.2023.10191364].

SAGE: Semantic-Aware Global Explanations for Named Entity Recognition

Rigutini, Leonardo
Supervision
2023-01-01

Abstract

In this paper, we present a post-hoc method to produce highly interpretable global rules to explain NLP classifiers. Rules are extracted with a data mining approach on a semantically enriched input representation, instead of using words/wordpieces solely. Semantic information yields more abstract and general rules that are both more explanatory and less complex, while being also better at reflecting the model behaviour.
2023
978-1-6654-8867-9
Zugarini, A., Rigutini, L. (2023). SAGE: Semantic-Aware Global Explanations for Named Entity Recognition. In 2023 International Joint Conference on Neural Networks (IJCNN) Proceedings (pp.1-8). New York : IEEE [10.1109/IJCNN54540.2023.10191364].
File in questo prodotto:
File Dimensione Formato  
SAGE_Semantic-Aware_Global_Explanations_for_Named_Entity_Recognition.pdf

non disponibili

Tipologia: PDF editoriale
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 1.05 MB
Formato Adobe PDF
1.05 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

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/11365/1245814