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

Realizing when a model is right for a wrong reason is not trivial andrequires a significant effort by model developers. In some cases an inputsalience method, which highlights the most important parts of the input, mayreveal problematic reasoning. But scrutinizing highlights over many datainstances is tedious and often infeasible. Furthermore, analyzing examples inisolation does not reveal general patterns in the data or in the model'sbehavior. In this paper we aim to address these issues and go fromunderstanding single examples to understanding entire datasets and models. Themethodology we propose is based on aggregated salience maps, to which we applyclustering, nearest neighbor search and visualizations. Using this methodologywe address multiple distinct but common model developer needs by showing howproblematic data and model behavior can be identified and explained -- anecessary first step for improving the model.

Understanding Text Classification Data and Models Using Aggregated Input Salience