TIGTEC : Token Importance Guided TExt Counterfactuals - Archive ouverte HAL Access content directly
Conference Papers Year : 2023

TIGTEC : Token Importance Guided TExt Counterfactuals

Abstract

Counterfactual examples explain a prediction by highlighting changes in an instance that flip the outcome of a classifier. This paper proposes TIGTEC, an efficient and modular method for generating sparse, plausible and diverse counterfactual explanations for textual data. TIGTEC is a text editing heuristic that targets and modifies words with high contribution using local feature importance. A new attention-based local feature importance is proposed. Counterfactual candidates are generated and assessed with a cost function integrating a semantic distance, while the solution space is efficiently explored in a beam search fashion. The conducted experiments show the relevance of TIGTEC in terms of success rate, sparsity, diversity and plausibility. This method can be used in both modelspecific or model-agnostic way, which makes it very convenient for generating counterfactual explanations.
Fichier principal
Vignette du fichier
TIGTEC__Token_Importance_Guided_TExt_Counterfactuals___ECML_PKDD_Springer_vlast (1).pdf (406.55 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04311749 , version 1 (28-11-2023)

Identifiers

Cite

Milan Bhan, Jean-Noël Vittaut, Nicolas Chesneau, Marie-Jeanne Lesot. TIGTEC : Token Importance Guided TExt Counterfactuals. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. ECML PKDD 2023, Sep 2023, Turin, Italy. pp.496-512, ⟨10.1007/978-3-031-43418-1_30⟩. ⟨hal-04311749⟩
21 View
20 Download

Altmetric

Share

Gmail Facebook X LinkedIn More