Transparent Neighborhood Approximation for Text Classifier Explanation
This addresses the problem of opaque explanation processes for users of text classifiers, though it is incremental as it builds on existing neighborhood construction methods.
The paper tackled the lack of transparency in generative model-based neighborhood construction for explaining text classifiers by introducing a probability-based editing method, XPROB, which achieved competitive performance and superior stability on two real-world datasets.
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.