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

Knowledge distillation is one of the primary methods of transferringknowledge from large to small models. However, it requires massivetask-specific data, which may not be plausible in many real-world applications.Data augmentation methods such as representation interpolation, tokenreplacement, or augmentation with models are applied to tackle this problem.However, these data augmentation methods either potentially cause shifts indecision boundaries (representation interpolation), are not expressive enough(token replacement), or introduce too much computational overhead (augmentationwith models). To this end, we propose AugPro (Augmentation with Projection), aneffective and efficient data augmentation method for distillation. Our methodbuilds on top of representation interpolation augmentation methods to maintainthe diversity of expressions and converts the augmented data to tokens to avoidshifting decision boundaries. It uses simple operations that come with littlecomputational overhead. The results on multiple GLUE tasks show that ourmethods can improve distillation performance by a large margin at a low timecost. Codes are available athttps://github.com/google-research/google-research/tree/master/augpro.

Augmentation with Projection: Towards an Effective and Efficient Data Augmentation Paradigm for Distillation