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

Post-hoc explanations for black box models have been studied extensively inclassification and regression settings. However, explanations for models thatoutput similarity between two inputs have received comparatively lesserattention. In this paper, we provide model agnostic local explanations forsimilarity learners applicable to tabular and text data. We first propose amethod that provides feature attributions to explain the similarity between apair of inputs as determined by a black box similarity learner. We then proposeanalogies as a new form of explanation in machine learning. Here the goal is toidentify diverse analogous pairs of examples that share the same level ofsimilarity as the input pair and provide insight into (latent) factorsunderlying the model's prediction. The selection of analogies can optionallyleverage feature attributions, thus connecting the two forms of explanationwhile still maintaining complementarity. We prove that our analogy objectivefunction is submodular, making the search for good-quality analogies efficient.We apply the proposed approaches to explain similarities between sentences aspredicted by a state-of-the-art sentence encoder, and between patients in ahealthcare utilization application. Efficacy is measured through quantitativeevaluations, a careful user study, and examples of explanations.

Analogies and Feature Attributions for Model Agnostic Explanation of Similarity Learners