An Analysis of LIME for Text Data - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

An Analysis of LIME for Text Data

Abstract

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.
Fichier principal
Vignette du fichier
lime_text.pdf (1.01 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-02935171 , version 1 (10-09-2020)
hal-02935171 , version 2 (23-05-2021)

Identifiers

Cite

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⟩
226 View
125 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More