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

The Mixup method has proven to be a powerful data augmentation technique inComputer Vision, with many successors that perform image mixing in a guidedmanner. One of the interesting research directions is transferring theunderlying Mixup idea to other domains, e.g. Natural Language Processing (NLP).Even though there already exist several methods that apply Mixup to textualdata, there is still room for new, improved approaches. In this work, weintroduce AttentionMix, a novel mixing method that relies on attention-basedinformation. While the paper focuses on the BERT attention mechanism, theproposed approach can be applied to generally any attention-based model.AttentionMix is evaluated on 3 standard sentiment classification datasets andin all three cases outperforms two benchmark approaches that utilize Mixupmechanism, as well as the vanilla BERT method. The results confirm that theattention-based information can be effectively used for data augmentation inthe NLP domain.

AttentionMix: Data augmentation method that relies on BERT attention mechanism