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

Leveraging knowledge from multiple tasks through introducing a small numberof task specific parameters into each transformer layer, also known asadapters, receives much attention recently. However, adding an extra fusionlayer to implement knowledge composition not only increases the inference timebut also is non-scalable for some applications. To avoid these issues, wepropose a two-stage knowledge distillation algorithm calledAdapterDistillation. In the first stage, we extract task specific knowledge byusing local data to train a student adapter. In the second stage, we distillthe knowledge from the existing teacher adapters into the student adapter tohelp its inference. Extensive experiments on frequently asked questionretrieval in task-oriented dialog systems validate the efficiency ofAdapterDistillation. We show that AdapterDistillation outperforms existingalgorithms in terms of accuracy, resource consumption and inference time.

AdapterDistillation: Non-Destructive Task Composition with Knowledge Distillation