English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The importance of neighborhood construction in local explanation methods hasbeen already highlighted in the literature. And several attempts have been madeto improve neighborhood quality for high-dimensional data, for example, texts,by adopting generative models. Although the generators produce more realisticsamples, the intuitive sampling approaches in the existing solutions leave thelatent space underexplored. To overcome this problem, our work, focusing onlocal model-agnostic explanations for text classifiers, proposes a progressiveapproximation approach that refines the neighborhood of a to-be-explaineddecision with a careful two-stage interpolation using counterfactuals aslandmarks. We explicitly specify the two properties that should be satisfied bygenerative models, the reconstruction ability and the locality-preservingproperty, to guide the selection of generators for local explanation methods.Moreover, noticing the opacity of generative models during the study, wepropose another method that implements progressive neighborhood approximationwith probability-based editions as an alternative to the generator-basedsolution. The explanation results from both methods consist of word-level andinstance-level explanations benefiting from the realistic neighborhood. Throughexhaustive experiments, we qualitatively and quantitatively demonstrate theeffectiveness of the two proposed methods.

Explaining text classifiers through progressive neighborhood approximation with realistic samples