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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Context plays an important role in human language understanding, thus it mayalso be useful for machines learning vector representations of language. Inthis paper, we explore an asymmetric encoder-decoder structure for unsupervisedcontext-based sentence representation learning. We carefully designedexperiments to show that neither an autoregressive decoder nor an RNN decoderis required. After that, we designed a model which still keeps an RNN as theencoder, while using a non-autoregressive convolutional decoder. We furthercombine a suite of effective designs to significantly improve model efficiencywhile also achieving better performance. Our model is trained on two differentlarge unlabelled corpora, and in both cases the transferability is evaluated ona set of downstream NLP tasks. We empirically show that our model is simple andfast while producing rich sentence representations that excel in downstreamtasks.

Speeding up Context-based Sentence Representation Learning with Non-autoregressive Convolutional Decoding