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

Self-training (ST) has prospered again in language understanding byaugmenting the fine-tuning of pre-trained language models when labeled data isinsufficient. However, it remains challenging to incorporate ST intoattribute-controllable language generation. Augmented by only self-generatedpseudo text, generation models over-emphasize exploitation of the previouslylearned space, suffering from a constrained generalization boundary. We revisitST and propose a novel method, DuNST to alleviate this problem. DuNST jointlymodels text generation and classification with a shared Variational AutoEncoderand corrupts the generated pseudo text by two kinds of flexible noise todisturb the space. In this way, our model could construct and utilize bothpseudo text from given labels and pseudo labels from available unlabeled text,which are gradually refined during the ST process. We theoretically demonstratethat DuNST can be regarded as enhancing exploration towards the potential realtext space, providing a guarantee of improved performance. Experiments on threecontrollable generation tasks show that DuNST could significantly boost controlaccuracy while maintaining comparable generation fluency and diversity againstseveral strong baselines.

DuNST: Dual Noisy Self Training for Semi-Supervised Controllable Text Generation