Transparent Neighborhood Approximation for Text Classifier Explanation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cai, Yi, Zimek, Arthur, Ntoutsi, Eirini, Wunder, Gerhard
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915033050513408
author Cai, Yi
Zimek, Arthur
Ntoutsi, Eirini
Wunder, Gerhard
author_facet Cai, Yi
Zimek, Arthur
Ntoutsi, Eirini
Wunder, Gerhard
contents Recent literature highlights the critical role of neighborhood construction in deriving model-agnostic explanations, with a growing trend toward deploying generative models to improve synthetic instance quality, especially for explaining text classifiers. These approaches overcome the challenges in neighborhood construction posed by the unstructured nature of texts, thereby improving the quality of explanations. However, the deployed generators are usually implemented via neural networks and lack inherent explainability, sparking arguments over the transparency of the explanation process itself. To address this limitation while preserving neighborhood quality, this paper introduces a probability-based editing method as an alternative to black-box text generators. This approach generates neighboring texts by implementing manipulations based on in-text contexts. Substituting the generator-based construction process with recursive probability-based editing, the resultant explanation method, XPROB (explainer with probability-based editing), exhibits competitive performance according to the evaluation conducted on two real-world datasets. Additionally, XPROB's fully transparent and more controllable construction process leads to superior stability compared to the generator-based explainers.
format Preprint
id arxiv_https___arxiv_org_abs_2411_16251
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Transparent Neighborhood Approximation for Text Classifier Explanation
Cai, Yi
Zimek, Arthur
Ntoutsi, Eirini
Wunder, Gerhard
Computation and Language
Machine Learning
Recent literature highlights the critical role of neighborhood construction in deriving model-agnostic explanations, with a growing trend toward deploying generative models to improve synthetic instance quality, especially for explaining text classifiers. These approaches overcome the challenges in neighborhood construction posed by the unstructured nature of texts, thereby improving the quality of explanations. However, the deployed generators are usually implemented via neural networks and lack inherent explainability, sparking arguments over the transparency of the explanation process itself. To address this limitation while preserving neighborhood quality, this paper introduces a probability-based editing method as an alternative to black-box text generators. This approach generates neighboring texts by implementing manipulations based on in-text contexts. Substituting the generator-based construction process with recursive probability-based editing, the resultant explanation method, XPROB (explainer with probability-based editing), exhibits competitive performance according to the evaluation conducted on two real-world datasets. Additionally, XPROB's fully transparent and more controllable construction process leads to superior stability compared to the generator-based explainers.
title Transparent Neighborhood Approximation for Text Classifier Explanation
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2411.16251