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

Privacy preservation is a crucial component of any real-world application.But, in applications relying on machine learning backends, privacy ischallenging because models often capture more than what the model was initiallytrained for, resulting in the potential leakage of sensitive information. Inthis paper, we propose an automatic and quantifiable metric that allows us toevaluate humans' perception of a model's ability to preserve privacy withrespect to sensitive variables. In this paper, we focus on saliency-basedexplanations, explanations that highlight regions of the input text, to inferinternal workings of a black box model. We use the degree with whichdifferences in interpretation of general vs privacy preserving models correlatewith sociolinguistic biases to inform metric design. We show how certaincommonly-used methods that seek to preserve privacy do not align with humanperception of privacy preservation leading to distrust about model's claims. Wedemonstrate the versatility of our proposed metric by validating its utilityfor measuring cross corpus generalization for both privacy and emotion.Finally, we conduct crowdsourcing experiments to evaluate the inclination ofthe evaluators to choose a particular model for a given purpose when modelexplanations are provided, and show a positive relationship with the proposedmetric. To the best of our knowledge, we take the first step in proposingautomatic and quantifiable metrics that best align with human perception ofmodel's ability for privacy preservation, allowing for cost-effective modeldevelopment.

Human-Imitating Metrics for Training and Evaluating Privacy Preserving Emotion Recognition Models Using Sociolinguistic Knowledge