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

Recent pre-trained language models (PLMs) achieved great success on manynatural language processing tasks through learning linguistic features andcontextualized sentence representation. Since attributes captured in stackedlayers of PLMs are not clearly identified, straightforward approaches such asembedding the last layer are commonly preferred to derive sentencerepresentations from PLMs. This paper introduces the attention-based poolingstrategy, which enables the model to preserve layer-wise signals captured ineach layer and learn digested linguistic features for downstream tasks. Thecontrastive learning objective can adapt the layer-wise attention pooling toboth unsupervised and supervised manners. It results in regularizing theanisotropic space of pre-trained embeddings and being more uniform. We evaluateour model on standard semantic textual similarity (STS) and semantic searchtasks. As a result, our method improved the performance of the base contrastivelearned BERT_base and variants.

Don't Judge a Language Model by Its Last Layer: Contrastive Learning with Layer-Wise Attention Pooling