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

As the applications of Natural Language Processing (NLP) in sensitive areaslike Political Profiling, Review of Essays in Education, etc. proliferate,there is a great need for increasing transparency in NLP models to build trustwith stakeholders and identify biases. A lot of work in Explainable AI hasaimed to devise explanation methods that give humans insights into the workingsand predictions of NLP models. While these methods distill predictions fromcomplex models like Neural Networks into consumable explanations, how humansunderstand these explanations is still widely unexplored. Innate humantendencies and biases can handicap the understanding of these explanations inhumans, and can also lead to them misjudging models and predictions as aresult. We designed a randomized survey-based experiment to understand theeffectiveness of saliency-based Post-hoc explainability methods in NaturalLanguage Processing. The result of the experiment showed that humans have atendency to accept explanations with a less critical view.

Testing the effectiveness of saliency-based explainability in NLP using randomized survey-based experiments