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

Zero-shot stance detection is challenging because it requires detecting thestance of previously unseen targets in the inference phase. The ability tolearn transferable target-invariant features is critical for zero-shot stancedetection. In this work, we propose a stance detection approach that canefficiently adapt to unseen targets, the core of which is to capturetarget-invariant syntactic expression patterns as transferable knowledge.Specifically, we first augment the data by masking the topic words ofsentences, and then feed the augmented data to an unsupervised contrastivelearning module to capture transferable features. Then, to fit a specifictarget, we encode the raw texts as target-specific features. Finally, we adoptan attention mechanism, which combines syntactic expression patterns withtarget-specific features to obtain enhanced features for predicting previouslyunseen targets. Experiments demonstrate that our model outperforms competitivebaselines on four benchmark datasets.

Zero-shot stance detection based on cross-domain feature enhancement by contrastive learning