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

Text classification tasks often encounter few shot scenarios with limitedlabeled data, and addressing data scarcity is crucial. Data augmentation withmixup has shown to be effective on various text classification tasks. However,most of the mixup methods do not consider the varying degree of learningdifficulty in different stages of training and generate new samples with onehot labels, resulting in the model over confidence. In this paper, we propose aself evolution learning (SE) based mixup approach for data augmentation in textclassification, which can generate more adaptive and model friendly pesudosamples for the model training. SE focuses on the variation of the model'slearning ability. To alleviate the model confidence, we introduce a novelinstance specific label smoothing approach, which linearly interpolates themodel's output and one hot labels of the original samples to generate new softfor label mixing up. Through experimental analysis, in addition to improvingclassification accuracy, we demonstrate that SE also enhances the model'sgeneralize ability.

Self-Evolution Learning for Mixup: Enhance Data Augmentation on Few-Shot Text Classification Tasks