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 augmentation techniques are widely used in text classification problemsto improve the performance of classifiers, especially in low-resourcescenarios. Whilst lots of creative text augmentation methods have beendesigned, they augment the text in a non-selective manner, which means the lessimportant or noisy words have the same chances to be augmented as theinformative words, and thereby limits the performance of augmentation. In thiswork, we systematically summarize three kinds of role keywords, which havedifferent functions for text classification, and design effective methods toextract them from the text. Based on these extracted role keywords, we proposeSTA (Selective Text Augmentation) to selectively augment the text, where theinformative, class-indicating words are emphasized but the irrelevant or noisywords are diminished. Extensive experiments on four English and Chinese textclassification benchmark datasets demonstrate that STA can substantiallyoutperform the non-selective text augmentation methods.

What Have Been Learned & What Should Be Learned? An Empirical Study of How to Selectively Augment Text for Classification