An Analysis of LIME for Text Data

Dina Mardaoui (1) , Damien Garreau (2, 3, 4)

1 EPU Nice -Polytech'Nice-Sophia - Ecole Polytechnice Universitaire de Nice
2 MAASAI - Modèles et algorithmes pour l’intelligence artificielle
3 LJAD - Laboratoire Jean Alexandre Dieudonné
4 UniCA - Université Côte d'Azur

Text data are increasingly handled in an automated fashion by machine learning algorithms. But the models handling these data are not always well-understood due to their complexity and are more and more often referred to as "black-boxes." Interpretability methods aim to explain how these models operate. Among them, LIME has become one of the most popular in recent years. However, it comes without theoretical guarantees: even for simple models, we are not sure that LIME behaves accurately. In this paper, we provide a first theoretical analysis of LIME for text data. As a consequence of our theoretical findings, we show that LIME indeed provides meaningful explanations for simple models, namely decision trees and linear models.

Mots clés: Interpretability; Machine learning; Natural language Processing

Domaines: Statistiques [math.ST]; Intelligence artificielle [cs.AI]; Machine Learning [stat.ML]

Dina Mardaoui, Damien Garreau. An Analysis of LIME for Text Data. AISTATS 2021 - 24th International Conference on Artificial Intelligence and Statistics, Apr 2021, Vienne, Austria. ⟨hal-02935171v2⟩